NNDL

This set of Neural Networks Multiple Choice Questions & Answers (MCQs) focuses on “Introduction″.
1. Why do we need biological neural networks?

a) to solve tasks like machine vision & natural language processing
b) to apply heuristic search methods to find solutions of problem
c) to make smart human interactive & user friendly system
d) all of the mentioned
View Answer
Answer: d
Explanation: These are the basic aims that a neural network achieve.
2. What is the trend in software nowadays?

a) to bring computer more & more closer to user
b) to solve complex problems
c) to be task specific
d) to be versatile
View Answer
Answer: a
Explanation: Software should be more interactive to the user, so that it can understand its problem in a better
fashion.
3. What’s the main point of difference between human & machine intelligence?
a) human perceive everything as a pattern while machine perceive it merely as data
b) human have emotions
c) human have more IQ & intellect
d) human have sense organs
View Answer
Answer: a
Explanation: Humans have emotions & thus form different patterns on that basis, while a machine(say
computer) is dumb & everything is just a data for him.
advertisement
4. What is auto-association task in neural networks?

a) find relation between 2 consecutive inputs
b) related to storage & recall task
c) predicting the future inputs
d) none of the mentioned
View Answer
Answer: b
Explanation: This is the basic definition of auto-association in neural networks.
5. Does pattern classification belongs to category of non-supervised learning?

a) yes
b) no
View Answer
Answer: b
Explanation: Pattern classification belongs to category of supervised learning.
6. In pattern mapping problem in neural nets, is there any kind of generalization involved between input &
output?
a) yes
b) no
View Answer
Answer: a
Explanation: The desired output is mapped closest to the ideal output & hence there is generalisation involved.
7. What is unsupervised learning?

a) features of group explicitly stated
b) number of groups may be known
c) neither feature & nor number of groups is known
View Answer
Answer: c
Explanation: Basic definition of unsupervised learning.
8. Does pattern classification & grouping involve same kind of learning?

a) yes
b) no
View Answer
Answer: b
Explanation: Pattern classification involves supervised learning while grouping is an unsupervised one.
9. Does for feature mapping there’s need of supervised learning?

a) yes
b) no
View Answer
Answer: b
Explanation: Feature mapping can be unsupervised, so it’s not a sufficient condition.
10. Example of a unsupervised feature map?

a) text recognition
b) voice recognition
c) image recognition
View Answer
Answer: b
Explanation: Since same vowel may occur in different context & its features vary over overlapping regions of
different vowels.
11. What is plasticity in neural networks?

a) input pattern keeps on changing
b) input pattern has become static
c) output pattern keeps on changing
d) output is static
View Answer
Answer: a
Explanation: Dynamic nature of input patterns in an AI(Artificial Intelligence) problem.
12. What is stability plasticity dilemma ?

a) system can neither be stable nor plastic
b) static inputs & categorization can’t be handled
c) dynamic inputs & categorization can’t be handled
View Answer
Answer: c
Explanation: If system is allowed to change its categorization according to inputs it cannot be used for patterns
classification & assessment.
13. Drawbacks of template matching are?

a) time consuming
b) highly restricted
c) more generalized
d) none of the the mentioned
View Answer
Answer: b
Explanation: Point to point pattern matching is carried out in the process
This set of Neural Networks Multiple Choice Questions & Answers (MCQs) focuses on “Characteristics – 1″.
1. What are the issues on which biological networks proves to be superior than AI networks?
a) robustness & fault tolerance
b) flexibility
c) collective computation
View Answer
Answer: d
Explanation: AI network should be all of the above mentioned.
2. The fundamental unit of network is

a) brain
b) nucleus
c) neuron
d) axon
View Answer
Answer: c
Explanation: Neuron is the most basic & fundamental unit of a network .
3. What are dendrites?

a) fibers of nerves
b) nuclear projections
c) other name for nucleus
View Answer
Answer: a
Explanation: Dendrites tree shaped fibers of nerves.
advertisement
4. What is shape of dendrites like

a) oval
b) round
c) tree
d) rectangular
View Answer
Answer: c
Explanation: Basic biological q&a.
5. Signal transmission at synapse is a?

a) physical process
b) chemical process
c) physical & chemical both
View Answer
Answer: b
Explanation: Since chemicals are involved at synapse , so its an chemical process.
6. How does the transmission/pulse acknowledged ?

a) by lowering electric potential of neuron body
b) by raising electric potential of neuron body
c) both by lowering & raising electric potential
View Answer
Answer: c
Explanation: There is equal probability of both.
7. When the cell is said to be fired?
a) if potential of body reaches a steady threshold values
b) if there is impulse reaction
c) during upbeat of heart
View Answer
Answer: a
Explanation: Cell is said to be fired if & only if potential of body reaches a certain steady threshold values.
8. Where does the chemical reactions take place in neuron?

a) dendrites
b) axon
c) synapses
d) nucleus
View Answer
Answer: c
Explanation: It is a simple biological fact.
9. Function of dendrites is?

a) receptors
b) transmitter
c) both receptor & transmitter
View Answer
Answer: a
Explanation: Dendrites are tree like projections whose function is only to receive impulse.
10. What is purpose of Axon?

a) receptors
b) transmitter
c) transmission
View Answer
Answer: c
Explanation: Axon is the body of neuron & thus cant be at ends of it so cant receive & transmit signals.
This set of Neural Networks online quiz focuses on “Characteristics – 2”.
1. What is approx size of neuron body(in micrometer)?

a) below 5
b) 5-10
c) 10-80
d) above 100
View Answer
Answer: c
Explanation: Average size of neuron body lies in the above limit.
2. What is the gap at synapses(in nanometer)?

a) 50
b) 100
c) 150
d) 200
View Answer
Answer: d
Explanation: It is near to 200nm.
3. What is charge at protoplasm in state of inactivity?

a) positive
b) negative
c) neutral
d) may be positive or negative
View Answer
Answer: b
Explanation: It is due to the presence of potassium ion on outer surface in neural fluid.
advertisement
4. What is the main constituent of neural liquid?

a) sodium
b) potassium
c) Iron
View Answer
Answer: a
Explanation: Potassium is the main constituent of neural liquid & responsible for potential on neuron body.
5. What is average potential of neural liquid in inactive state?

a) +70mv
b) +35mv
c) -35mv
d) -70mv
View Answer
Answer: d
Explanation: It is a basic fact, founded out by series of experiments conducted by neural scientist.
6. At what potential does cell membrane looses it impermeability against Na+ ions?
a) -50mv
b) -35mv
c) -60mv
d) -65mv
View Answer
Answer: c
Explanation: Cell membrane looses it impermeability against Na+ ions at -60mv.
7. What is effect on neuron as a whole when its potential get raised to -60mv?
a) it get fired
b) no effect
c) it get compressed
d) it expands
View Answer
Answer: a
Explanation: Cell membrane looses it impermeability against Na+ ions at -60mv.
8. The membrane which allows neural liquid to flow will?

a) never be imperturbable to neural liquid
b) regenerate & retain its original capacity
c) only the certain part get affected, while rest becomes imperturbable again
View Answer
Answer: b
Explanation: Each cell of human body(internal) has regenerative capacity.
9. How fast is propagation of discharge signal in cells of human brain?

a) less than 0.1m/s
b) 0.5-2m/s
c) 2-5m/s
d) 5-10m/s
View Answer
Answer: b
Explanation: The process is very fast but comparable to the length of neuron.
10. What is the function of neurotransmitter ?

a) they transmit data directly at synapse to other neuron
b) they modify conductance of post synaptic membrane for certain ions
c) cause polarisation or depolarisation
d) both polarisation & modify conductance of membrane
View Answer
Answer: d
Explanation: Excitatory & inhibilatory activities are result of these two process
This set of Neural Networks Questions & Answers for entrance exams focuses on “Characteristics – 3”.
1. The cell body of neuron can be analogous to what mathamatical operation?

a) summing
b) differentiator
c) integrator
View Answer
Answer: a
Explanation: Because adding of potential(due to neural fluid) at different parts of neuron is the reason of its
firing.
2. What is the critical threshold voltage value at which neuron get fired?
a) 30mv
b) 20mv
c) 25mv
d) 10mv
View Answer
Answer: d
Explanation: This critical is founded by series of experiments conducted by neural scientist.
3. Does there is any effect on particular neuron which got repeatedly fired ?
a) yes
b) no
View Answer
Answer: a
Explanation: The strength of neuron to fire in future increases.
advertisement
4. What is name of above mechanism?

a) hebb rule learning
b) error correction learning
c) memory based learning
View Answer
Answer: a
Explanation: It follows from basic definition of hebb rule learning.
5. What is hebb’s rule of learning

a) the system learns from its past mistakes
b) the system recalls previous reference inputs & respective ideal outputs
c) the strength of neural connection get modified accordingly
View Answer
Answer:c
Explanation: The strength of neuron to fire in future increases, if it is fired repeatedly.
6. Are all neuron in brain are of same type?
a) yes
b) no
View Answer
Answer: b
Explanation: Follows from the fact no two body cells are exactly similar in human body, even if they belong to
same class.
7. What is estimate number of neurons in human cortex?

a) 108
b) 105
c) 1011
d) 1020
View Answer
Answer: c
Explanation: It is a fact !
8. what is estimated density of neuron per mm^2 of cortex?

a) 15*(102)
b) 15*(104)
c) 15*(103)
d) 5*(104)
View Answer
Answer: b
Explanation: It is a biological fact !
9. Why can’t we design a perfect neural network?

a) full operation is still not known of biological neurons
b) number of neuron is itself not precisely known
c) number of interconnection is very large & is very complex
View Answer
Answer: d
Explanation: These are all fundamental reasons, why can’t we design a perfect neural network !
10. How many synaptic connection are there in human brain?

a) 1010
b) 1015
c) 1020
d) 105
View Answer
Answer: b
Explanation: You can estimate this value from number of neurons in human cortex & their density.
This set of Neural Networks Multiple Choice Questions & Answers (MCQs) focuses on “Backpropagation
Algorithm″.
1. What is the objective of backpropagation algorithm?

a) to develop learning algorithm for multilayer feedforward neural network
b) to develop learning algorithm for single layer feedforward neural network
c) to develop learning algorithm for multilayer feedforward neural network, so that network can be trained to
capture the mapping implicitly
View Answer
Answer: c
Explanation: The objective of backpropagation algorithm is to to develop learning algorithm for multilayer
feedforward neural network, so that network can be trained to capture the mapping implicitly.
2. The backpropagation law is also known as generalized delta rule, is it true?
a) yes
b) no
View Answer
Answer: a
Explanation: Because it fulfils the basic condition of delta rule.
3. What is true regarding backpropagation rule?

a) it is also called generalized delta rule
b) error in output is propagated backwards only to determine weight updates
c) there is no feedback of signal at nay stage
View Answer
Answer: d
Explanation: These all statements defines backpropagation algorithm.
advertisement
4. There is feedback in final stage of backpropagation algorithm?

a) yes
b) no
View Answer
Answer: b
Explanation: No feedback is involved at any stage as it is a feedforward neural network.
5. What is true regarding backpropagation rule?

a) it is a feedback neural network
b) actual output is determined by computing the outputs of units for each hidden layer
c) hidden layers output is not all important, they are only meant for supporting input and output layers
View Answer
Answer: b
Explanation: In backpropagation rule, actual output is determined by computing the outputs of units for each
hidden layer.
6. What is meant by generalized in statement “backpropagation is a generalized delta rule” ?

a) because delta rule can be extended to hidden layer units
b) because delta is applied to only input and output layers, thus making it more simple and generalized
c) it has no significance
View Answer
Answer: a
Explanation: The term generalized is used because delta rule could be extended to hidden layer units.
7. What are general limitations of back propagation rule?

a) local minima problem
b) slow convergence
c) scaling
View Answer
Answer: d
Explanation: These all are limitations of backpropagation algorithm in general.
8. What are the general tasks that are performed with backpropagation algorithm?
a) pattern mapping
b) function approximation
c) prediction
View Answer
Answer: d
Explanation: These all are the tasks that can be performed with backpropagation algorithm in general.
9. Does backpropagaion learning is based on gradient descent along error surface?

a) yes
b) no
c) cannot be said
d) it depends on gradient descent but not error surface
View Answer
Answer: a
Explanation: Weight adjustment is proportional to negative gradient of error with respect to weight.
10. How can learning process be stopped in backpropagation rule?

a) there is convergence involved
b) no heuristic criteria exist
c) on basis of average gradient value
View Answer
Answer: c
Explanation: If average gadient value fall below a preset threshold value, the process may be stopped
This set of Neural Networks Multiple Choice Questions & Answers (MCQs) focuses on “Boltzman Machine – 1″.
1. Probability of error in recall of stored patterns can be reduced if?

a) patterns are stored appropriately
b) inputs are captured appropriately
c) weights are chosen appropriately
View Answer
Answer: c
Explanation: Probability of error in recall of stored patterns can be reduced if weights are chosen appropriately.
2. What is pattern environment?

a) probability of desired patterns
b) probability of given patterns
c) behaviour of system
View Answer
Answer: d
Explanation: Pattern environment is probability distribution of given patterns.
3. For what purpose is pattern environment useful?

a) determining structure
b) determining desired outputs
c) determining future inputs
View Answer
Answer: d
Explanation: Pattern environment is useful for determining weights.
advertisement
4. What should be the aim of training procedure in boltzman machine of feedback networks?
a) to capture inputs
b) to feedback the captured outputs
c) to capture the behaviour of system
View Answer
Answer: d
Explanation: The training procedure should try to capture the pattern environment.
5. What consist of boltzman machine?

a) fully connected network with both hidden and visible units
b) asynchronous operation
c) stochastic update
View Answer
Answer: d
Explanation: Boltzman machine consist of fully connected network with both hidden and visible units operating
asynchronously with stochastic update.
6. By using which method, boltzman machine reduces effect of additional stable states?
a) no such method exist
b) simulated annealing
c) hopfield reduction
View Answer
Answer: b
Explanation: boltzman machine uses simulated annealing to reduce the effect of additional stable states.
7. For which other task can boltzman machine be used?

a) pattern mapping
b) feature mapping
c) classification
d) pattern association
View Answer
Answer: d
Explanation: Boltzman machine can be used for pattern association.
8. How are energy minima related to probability of occurrence of corresponding patterns in the environment?
a) directly
b) inversely
c) directly or inversely
d) no relation
View Answer
Answer: a
Explanation: Energy minima is directly related to probability of occurrence of corresponding patterns in the
environment.
9. Is exact representation of pattern environment possible?

a) yes
b) no
View Answer
Answer: b
Explanation: Exact representation of pattern environment is not possible.
10. What may be the reasons for non zero probability of error in recalling?
a) spurious stable states
b) approximation in pattern environment representation
c) extra stable states
View Answer
Answer: d
Explanation: These all are the primary reasons for existence of non zero probability of error.
This set of Neural Networks Multiple Choice Questions & Answers focuses on “Boltzman Machine – 2”.
1. For what purpose Feedback neural networks are primarily used?
a) classification
b) feature mapping
c) pattern mapping
View Answer
Answer: d
Explanation: Feedback neural networks are primarily used for pattern storage.
2. Presence of false minima will have what effect on probability of error in recall?
a) directly
b) inversely
c) no effect
d) directly or inversely
View Answer
Answer: a
Explanation: Presence of false minima will increase the probability of error in recall.
3. How is effect false minima reduced

a) deterministic update of weights
b) stochastic update of weights
c) deterministic or stochastic update of weights
View Answer
Answer: b
Explanation: Presence of false minima can be reduced by stochastic update.
advertisement
4. Is Boltzman law practical for implementation?

a) yes
b) no
View Answer
Answer: b
Explanation: Boltzman law is too slow for implementation.
5. For practical implementation what type of approximation is used on boltzman law?

a) max field approximation
b) min field approximation
c) hopfield approximation
View Answer
Answer: d
Explanation: For practical implementation mean field approximation is used.
6. What happens when we use mean field approximation with boltzman learning?
a) it slows down
b) it get speeded up
c) nothing happens
d) may speedup or speed down
View Answer
Answer: b
Explanation: Boltzman learning get speeded up using mean field approximation.
7. Approximately how much times the boltzman learning get speeded up using mean field approximation?
a) 5-10
b) 10-30
c) 30-50
d) 50-70
View Answer
Answer: b
Explanation: Boltzman learning get speeded up 10-30 using mean field approximation.
8.False minima can be reduced by deterministic updates?

a) yes
b) no
View Answer
Answer: b
Explanation: Presence of false minima can be reduced by stochastic update.
9. In boltzman learning which algorithm can be used to arrive at equilibrium?

a) hopfield
b) mean field
c) hebb
View Answer
Answer: d
Explanation: Metropolis algorithm can be used to arrive at equilibrium.
10. Boltzman learning is a?

a) fast process
b) steady process
c) slow process
View Answer
Answer: d
Explanation: Boltzman learning is a slow process
This set of Neural Networks Multiple Choice Questions & Answers (MCQs) focuses on “Stochastic Networks″.
1. p(s=1|x) = 1/(1+exp(-x/T))) ,where ‘s’ is the output given the activation ‘x’ is a?
a) hopfield network
b) sigma network
c) stochastic network
View Answer
Answer: c
Explanation: This is the basic equation of a stochastic network.
2. Does a stochastic network will evolve differently each time it is run?

a) yes
b) no
View Answer
Answer: a
Explanation: As trajectory of the state of the network becomes a sample function of a random process.
3. In case of deterministic update, what kind of equilibrium is reached?

a) static
b) dynamic
c) neutral
View Answer
Answer: a
Explanation: In case of deterministic update, static equilibrium is reached.
advertisement
4. In case of stochastic update, can static equilibrium be reached?

a) yes
b) no
View Answer
Answer: b
Explanation: There will never be a static equilibrium in stochastic network.
5. In case of stochastic update, what kind of equilibrium is reached?

a) static
b) dynamic
c) neutral
d) equilibrium not possible
View Answer
Answer: b
Explanation: In case of stochastic update, dynamic equilibrium is reached.
6. Is it possible in stochastic network that average state of network doesn’t change with time?
a) yes
b) no
View Answer
Answer: a
Explanation: Dynamic equilibrium is possible in stochastic network.
7. What can be the possible reason for thermal equilibrium in stochastic networks?
a) probability distribution of states changes and compensates
b) probability distribution change with only update
c) probability distribution does not change with time
d) none of the mentionedstochastic network exhibits stable states
View Answer
Answer: c
Explanation: Probability distribution does not change with time is the only reason for thermal equilibrium in
stochastic networks.
8. Can networks with symmetric weight reach thermal equilibrium?

a) yes
b) no
View Answer
Answer: a
Explanation: Networks with symmetric weight reach thermal equilibrium at a given temperature.
9. When activation value is determined by using the average of fluctuations of outputs from other units, it is
known as?
a) maximum field approximation
b) median field approximation
c) minimum field approximation
View Answer
Answer: d
Explanation: It is known as mean field approximation.
10. Where does a stochastic network exhibits stable states ?

a) at any temperature
b) above critical temperature
c) at critical temperature
d) below critical temperature
View Answer
Answer: d
Explanation: Stochastic network exhibits stable states below critical temperature.
This set of Neural Networks MCQs focuses on “Hopfield Model – 2”.

1. In hopfield network with symmetric weights, energy at each state may?
a) increase
b) decrease
c) decrease or remain same
d) decrease or increase
View Answer
Answer: chis set of Neural Networks Multiple Choice Questions & Answers (MCQs) focuses on “Hopfield Model
– 1″.
1. How can states of units be updated in hopfield model?

a) synchronously
b) asynchronously
c) synchronously and asynchronously
View Answer
Answer: c
Explanation: States of units be updated synchronously and asynchronously in hopfield model.
2. What is synchronous update in hopfield model?

a) all units are updated simultaneously
b) a unit is selected at random and its new state is computed
c) a predefined unit is selected and its new state is computed
View Answer
Answer: a
Explanation: In synchronous update, all units are updated simultaneously.
3. What is asynchronous update in hopfield model?

View Answer
Answer: b
Explanation: In asynchronous update, a unit is selected at random and its new state is computed.
advertisement
4. Asynchronous update ensures that the next state is atmost unit hamming distance from current state, is that
true?
a) yes
b) no
View Answer
Answer: a
Explanation: Asynchronous update ensures that the next state is at most unit hamming distance from current
state.
5. If pattern is to be stored, then what does stable state should have updated value of?
a) current sate
b) next state
c) both current and next state
View Answer
Answer: a
Explanation: Stable state should have updated value of current sate.
6. For symmetric weights there exist?

a) basins of attraction corresponding to energy minimum
b) false wells
c) fluctuations in energy landscape
d) none of he mentioned
View Answer
Answer: a
Explanation: For symmetric weights there exist a stable point.
7. If connections are not symmetric then basins of attraction may correspond to?
a) oscillatory regions
b) stable regions
c) chaotic regions
d) oscillatory or chaotic regions
View Answer
Answer: d
Explanation: If connections are not symmetric then basins of attraction may correspond to oscillatory or chaotic
regions.
8. For analysis of storage capacity what are the conditions imposed on hopfield model?
a) symmetry of weights
b) asynchronous update
c) symmetry of weights and asynchronous update
View Answer
Answer: c
Explanation: For analysis of storage capacity, symmetry of weights and asynchronous update conditions are
imposed on hopfield model.
9. What is gradient descent?

a) method to find the absolute minimum of a function
b) method to find the absolute maximum of a function
c) maximum or minimum, depends on the situation
View Answer
Answer: a
Explanation: Gradient descent gives absolute minimum of a function.
10. If connections are not symmetric then basins of attraction may correspond to oscillatory or stable regions, is
that true?
a) yes
b) no
View Answer
Answer: b
Explanation: Asymmetric weight can’t lead to stable regions
his set of Neural Networks Multiple Choice Questions & Answers (MCQs) focuses on “Hopfield Model – 1″.
1. How can states of units be updated in hopfield model?

a) synchronously
b) asynchronously
c) synchronously and asynchronously
View Answer
Answer: c
Explanation: States of units be updated synchronously and asynchronously in hopfield model.
2. What is synchronous update in hopfield model?

View Answer
Answer: a
Explanation: In synchronous update, all units are updated simultaneously.
3. What is asynchronous update in hopfield model?

View Answer
Answer: b
Explanation: In asynchronous update, a unit is selected at random and its new state is computed.
advertisement
4. Asynchronous update ensures that the next state is atmost unit hamming distance from current state, is that
true?
a) yes
b) no
View Answer
Answer: a
Explanation: Asynchronous update ensures that the next state is at most unit hamming distance from current
state.
5. If pattern is to be stored, then what does stable state should have updated value of?
a) current sate
b) next state
c) both current and next state
View Answer
Answer: a
Explanation: Stable state should have updated value of current sate.
6. For symmetric weights there exist?

a) basins of attraction corresponding to energy minimum
b) false wells
c) fluctuations in energy landscape
d) none of he mentioned
View Answer
Answer: a
Explanation: For symmetric weights there exist a stable point.
7. If connections are not symmetric then basins of attraction may correspond to?
a) oscillatory regions
b) stable regions
c) chaotic regions
d) oscillatory or chaotic regions
View Answer
Answer: d
Explanation: If connections are not symmetric then basins of attraction may correspond to oscillatory or chaotic
regions.
8. For analysis of storage capacity what are the conditions imposed on hopfield model?
a) symmetry of weights
b) asynchronous update
c) symmetry of weights and asynchronous update
View Answer
Answer: c
Explanation: For analysis of storage capacity, symmetry of weights and asynchronous update conditions are
imposed on hopfield model.
9. What is gradient descent?

a) method to find the absolute minimum of a function
b) method to find the absolute maximum of a function
c) maximum or minimum, depends on the situation
View Answer
Answer: a
Explanation: Gradient descent gives absolute minimum of a function.
10. If connections are not symmetric then basins of attraction may correspond to oscillatory or stable regions, is
that true?
a) yes
b) no
View Answer
Answer: b
Explanation: Asymmetric weight can’t lead to stable regions
Explanation: Energy of the network cant increase as it may then lead to instability.
2. In hopfield model with symmetric weights, network can move to?

a) lower
b) higher
c) lower or higher
d) lower or same
View Answer
Answer: d
Explanation: In hopfield model with symmetric weights, network can move to lower or same state.
3. Can error in recall due to false minima be reduced?

a) yes
b) no
View Answer
Answer: a
Explanation: There are generally two methods to reduce error in recall due to false minima.
advertisement
4. How can error in recall due to false minima be reduced?

a) deterministic update for states
b) stochastic update for states
c) not possible
View Answer
Answer: b
Explanation: Error in recall due to false minima can be reduced by stochastic update for states.
5. Energy at each state in hopfield with symmetric weights network may increase or decrease?
a) yes
b) no
View Answer
Answer: b
Explanation: Energy of the network cant increase as it may then lead to instability.
6. Pattern storage problem which cannot be represented by a feedback network of given size can be called as?
a) easy problems
b) hard problems
c) no such problem exist
View Answer
Answer: b
Explanation: Pattern storage problem which cannot be represented by a feedback network of given size are
known as hard problems.
7. What is the other way to reduce error in recall due to false minima apart from stochastic update?
a) no other method exist
b) by storing desired patterns at lowest energy minima
c) by storing desired patterns at energy maxima
View Answer
Answer: b
Explanation: Error in recall due to false minima can be reduced by stochastic update or by storing desired
patterns at lowest energy minima.
8. How can error in recall due to false minima be further reduced?

a) using suitable activation dynamics
b) cannot be further reduced
c) by storing desired patterns at energy maxima
View Answer
Answer: a
Explanation: Error in recall due to false minima can further be reduced by using suitable activation dynamics.
9. As temperature increase, what happens to stochastic update?

a) increase in update
b) decrease in update
c) no change
View Answer
Answer: c
Explanation: Temperature doesn’t effect stochastic update.
10. Why does change in temperature doesn’t effect stochastic update?

a) shape landscape depends on the network and its weights which varies accordingly and compensates the
effect
b) shape landscape depends on the network and its weights which is fixed
c) shape landscape depends on the network, its weights and the output function which varies accordingly and
compensates the effect
d) shape landscape depends on the network, its weights and the output function which is fixed
View Answer
Answer: d
Explanation: Change in temperature doesn’t effect stochastic update because shape landscape depends on
the network, its weights and the output function which is fixed.
This set of Neural Networks Multiple Choice Questions & Answers (MCQs) focuses on “Associative Memories″.
1. What are the tasks that cannot be realised or recognised by simple networks?
a) handwritten characters
b) speech sequences
c) image sequences
View Answer
Answer: d
Explanation: These all are complex recognition tasks.
2. Can data be stored directly in associative memory?
a) yes
b) no
View Answer
Answer: b
Explanation: Data cannot be stored directly in associative memory.
3. If the weight matrix stores the given patterns, then the network becomes?
a) autoassoiative memory
b) heteroassociative memory
c) multidirectional assocative memory
d) temporal associative memory
View Answer
Answer: a
Explanation: If the weight matrix stores the given patterns, then the network becomes autoassoiative memory.
advertisement
4. If the weight matrix stores association between a pair of patterns, then network becomes?
View Answer
Answer: b
Explanation: If the weight matrix stores the given patterns, then the network becomes heteroassociative
memory.
5. If the weight matrix stores multiple associations among several patterns, then network becomes?
View Answer
Answer: a
Explanation: If the weight matrix stores the given patterns, then the network becomes multidirectional
assocative memory.
6. If the weight matrix stores association between adjacent pairs of patterns, then network becomes?
View Answer
Answer: a
Explanation: If the weight matrix stores the given patterns, then the network becomes temporal associative
memory.
7. Heteroassociative memory is also known as?

a) unidirectional memory
b) bidirectional memory
View Answer
Answer: b
Explanation: Heteroassociative memory is also known as bidirectional memory.
8. What are some of desirable characteristics of associative memories?

a) ability to store large number of patterns
b) fault tolerance
c) able to recall, even for input pattern is noisy
View Answer
Answer: d
Explanation: These all are desirable characteristics of associative memories.
9. What is the objective of BAM?

a) to store pattern pairs
b) to recall pattern pairs
c) to store a set of pattern pairs and they can be recalled by giving either of pattern as input
View Answer
Answer: c
Explanation: The objective of BAM i.e Bidirectional Associative Memory, is to store a set of pattern pairs and
they can be recalled by giving either of pattern as input.
10. BAM is a special case of MAM, is that true?

a) yes
b) no
View Answer
Answer: a
Explanation: BAM i.e Bidirectional Associative Memory is a special case of MAM i.e Multidirectional Associative
Memory.
This set of Neural Networks Multiple Choice Questions & Answers (MCQs) focuses on “Multi Layer
Feedforward Neural Network″.
1. What is the use of MLFFNN?

a) to realize structure of MLP
b) to solve pattern classification problem
c) to solve pattern mapping problem
d) to realize an approximation to a MLP
View Answer
Answer: d
Explanation: MLFFNN stands for multilayer feedforward network and MLP stands for multilayer perceptron.
2. What is the advantage of basis function over mutilayer feedforward neural networks?
a) training of basis function is faster than MLFFNN
b) training of basis function is slower than MLFFNN
c) storing in basis function is faster than MLFFNN
View Answer
Answer: a
Explanation: The main advantage of basis function is that the training of basis function is faster than MLFFNN.
3. Why is the training of basis function is faster than MLFFNN?

a) because they are developed specifically for pattern approximation
b) because they are developed specifically for pattern classification
c) because they are developed specifically for pattern approximation or classification
View Answer
Answer: c
Explanation: Training of basis function is faster than MLFFNN because they are developed specifically for
pattern approximation or classification.
advertisement
4. Pattern recall takes more time for?

a) MLFNN
b) Basis function
c) Equal for both MLFNN and basis function
d) None of the mentioned
View Answer
Answer: b
Explanation: The first layer of basis function involves computations.
5. In which type of networks training is completely avoided?

a) GRNN
b) PNN
c) GRNN and PNN
View Answer
Answer: c
Explanation: In GRNN and PNN networks training is completely avoided.
6. What does GRNN do?

a) function approximation task
b) pattern classification task
c) function approximation and pattern classification task
View Answer
Answer: a
Explanation: GRNN stand for Generalized Regression Neural Networks.
7. What does PNN do?

a) function approximation task
b) pattern classification task
c) function approximation and pattern classification task
View Answer
Answer: b
Explanation: PNN stand for Probabilistic Neural Networks.
8. Th CPN provides practical approach for implementing?

a) patter approximation
b) pattern classification
c) pattern mapping
d) pattern clustering
View Answer
Answer: c
Explanation: CPN i.e counterpropagation network provides a practical approach for implementing pattern
mapping.
9. What consist of a basic counterpropagation network?

a) a feedforward network only
b) a feedforward network with hidden layer
c) two feedforward network with hidden layer
View Answer
Answer: c
Explanation: Counterpropagation network consist of two feedforward network with a common hidden layer.
10. How does the name counterpropagation signifies its architecture?

a) its ability to learn inverse mapping functions
b) its ability to learn forward mapping functions
c) its ability to learn forward and inverse mapping functions
View Answer
Answer: c
Explanation: Counterpropagation network has ability to learn forward and inverse mapping functions
This set of Neural Networks Multiple Choice Questions & Answers (MCQs) focuses on “Applications Of Neural
Networks – 1″.
1. Which application out of these of robots can be made of single layer feedforward network?
a) wall climbing
b) rotating arm and legs
c) gesture control
d) wall following
View Answer
Answer: d
Explanation: Wall folloing is a simple task and doesn’t require any feedback.
2. Which is the most direct application of neural networks?

a) vector quantization
b) pattern mapping
c) pattern classification
d) control applications
View Answer
Answer: c
Explanation: Its is the most direct and multilayer feedforward networks became popular because of this.
3. What are pros of neural networks over computers?

a) they have ability to learn b examples
b) they have real time high computational rates
c) they have more tolerance
View Answer
Answer: d
Explanation: Because of their parallel structure, they have high computational rates than conventional
computers, so all are true.
advertisement
4. what is true about single layer associative neural networks?

a) performs pattern recognition
b) can find the parity of a picture
c) can determine whether two or more shapes in a picture are connected or not
View Answer
Answer: a
Explanation: It can only perform pattern recognition, rest is not true for a single layer neural.
5. which of the following is false?

a) neural networks are artificial copy of the human brain
b) neural networks have high computational rates than conventional computers
c) neural networks learn by examples
View Answer
Answer: d
Explanation: All statements are true for a neural network.
6. For what purpose, hamming network is suitable?

a) classification
b) association
c) pattern storage
View Answer
Answer: a
Explanation: Hamming network performs template matching between stored templates and inputs.
7. What happens in upper subnet of the hamming network?

a) classification
b) storage
c) output
View Answer
Answer: d
Explanation: In upper subnet, competitive interaction among units take place.
8. The competition in upper subnet of hamming network continues till?

a) only one unit remains negative
b) all units are destroyed
c) output of only one unit remains positive
View Answer
Answer: c
Explanation: The competition in upper subnet of hamming network continues till output of only one unit remains
positive.
9. What does the activation value of winner unit is indicative of?

a) greater the degradation more is the activation value of winning units
b) greater the degradation less is the activation value of winning units
c) greater the degradation more is the activation value of other units
d) greater the degradation less is the activation value of other units
View Answer
Answer: b
Explanation: Simply, greater the degradation less is the activation value of winning units.
10. What does the matching score at first layer in recognition hamming network is indicative of?
a) dissimilarity of input pattern with patterns stored
b) noise immunity
c) similarity of input pattern with patterns stored
View Answer
Answer: c
Explanation: Matching score is simply a indicative of similarity of input pattern with patterns stored
This set of Neural Networks online test focuses on “Applications Of Neural Networks – 2”.
1. Can Invariances be build as static functions in the structure?

a) yes
b) no
View Answer
Answer: b
Explanation: Invariances have to be dynamically estimated from data.
2. What is the objective of associative memories?

a) to store patters
b) to recall patterns
c) to store association between patterns
View Answer
Answer: d
Explanation: The objective of associative memories is to store association between patterns for later recall of
one of patterns given the other.
3. Is it possible to capture implicit reasoning process by patten classification network?

a) yes
b) maybe
c) no
d) cannot be determined
View Answer
Answer: a
Explanation: For example neural network for contract bridge game.
advertisement
4. Are classification methods based on correlation matching using moment features useful for problems of
handwritten characters?
a) yes
b) no
View Answer
Answer: b
Explanation: Because different parts of handwritten characters are deformed differently.
5. Associative memory, if used in feedback structure of hopfield type can function as?
a) data memory
b) cluster
c) content addressable memory
View Answer
Answer: c
Explanation: Associative memory, if used in feedback structure of hopfield type can function as content
addressable memory.
6. In feedforward network, the associations corresponding to input – output patterns are stored in?
a) activation state
b) output layer
c) hidden layer
View Answer
Answer: d
Explanation: In feedforward network, the associations corresponding to input – output patterns are stored in
weights of the network.
7. Which is one of the application of associative memories?

a) direct pattern recall
b) voice signal recall
c) mapping of the signal
d) image pattern recall from noisy clues
View Answer
Answer: d
Explanation: The objective of associative memories is to store association between patterns for later recall of
one of patterns given the other, so noisy versions of the same image can be recalled.
8. How can optimization be applied in images?

a) by use of simulated annealing
b) by attaching a feedback network
c) by adding an additional hidden layer
View Answer
Answer: a
Explanation: Optimization be applied in images by use of simulated annealing to formulate the problem as
energy minimization problem.
9. In control applications, how many ways are there to control a plant?

a) 1
b) 2
c) 4
d) infinite
View Answer
Answer: b
Explanation: Open loop and feedback loop are the two ways.
10. Neuro – Fuzzy systems can lead to more powerful neural network?
a) yes
b) no
c) may be
d) cannot be determined
View Answer
Answer: a
Explanation: If fuzzy logic is incorporated into conventional ANN models, more powerful systems can be
created.
12/5/21, 11:23 PM Neural Networks - Artificial Intelligence MCQ Questions - Letsfindcourse
(https://letsfindcourse.com) 
Learn Programming For FREE, Click Here to Visit Our Youtube Channel. ×
(https://www.youtube.com/channel/UCcvvHiJ5dbg_bvMwA4vWETA?sub_confirmation=1)
AI Neural Networks MCQ

Neural Networks MCQs : This section focuses on "Neural Networks" in Artificial
Intelligence. These Multiple Choice Questions (mcq) should be practiced to improve
the AI skills required for various interviews (campus interviews, walk-in interviews,
company interviews), placements, entrance exams and other competitive
examinations.
1. Who was the inventor of the first neurocomputer?
A. Dr. John Hecht-Nielsen
B. Dr. Robert Hecht-Nielsen
C. Dr. Alex Hecht-Nielsen
D. Dr. Steve Hecht-Nielsen
View Answer
Ans : B
Explanation: The inventor of the first neurocomputer, Dr. Robert Hecht-Nielsen.
2. How many types of Artificial Neural Networks?
A. 2
B. 3
C. 4
D. 5
View Answer
Ans : A
Explanation: There are two Artificial Neural Network topologies : FeedForward and Feedback.
https://letsfindcourse.com/ai-mcq-questions/artificial-intelligence-neural-networks-mcq 2/6
3. In which ANN, loops(https://letsfindcourse.com)

are allowed?

A. FeedForward ANN
B. FeedBack ANN
C. Both A and B
D. None of the Above
View Answer
Ans : B
Explanation: FeedBack ANN loops are allowed. They are used in content addressable memories.
4. What is the full form of BN in Neural Networks?
A. Bayesian Networks
B. Belief Networks
C. Bayes Nets
D. All of the above
View Answer
Ans : D
Explanation: The full form BN is Bayesian networks and Bayesian networks are also called Belief
Networks or Bayes Nets.
Online Machine Learning
Free comparison tool for finding
Machine Learning courses online.
Coursary Open
5. What is the name of node which take binary values TRUE (T) and FALSE
(F)?
A. Dual Node
B. Binary Node
C. Two-way Node
D. Ordered Node
View Answer
Ans : B
Explanation: Boolean nodes : They represent propositions, taking binary values TRUE (T) and
FALSE (F).
6. What is an auto-associative network?
A. a neural network that contains no loops
B. a neural network that contains feedback
C. a neural network that has only one loop
D. a single layer feed-forward neural network with pre-processing
View Answer
Ans : B
Explanation: An auto-associative network is equivalent to a neural network that contains feedback.

The number of feedback paths(loops) does not have to be one.
7. What is Neuro software?
A. A software used to analyze neurons
B. It is powerful and easy neural network
C. Designed to aid experts in real world
D. It is software used by Neurosurgeon
View Answer
Ans : B
Explanation: Neuro software is powerful and easy neural network.
8. Neural Networks are complex ______________ with many parameters.
A. Linear Functions
B. Nonlinear Functions
C. Discrete Functions
D. Exponential Functions
View Answer
Ans : A
Explanation: Neural networks are complex linear functions with many parameters.
9. Which of the following is not the promise of artificial neural network?
A. It can explain result
B. It can survive the failure of some nodes
C. It has inherent parallelism
D. It can handle noise
View Answer
Ans : A
Explanation: The artificial Neural Network (ANN) cannot explain result.
10. The output at each node is called_____.
A. node value
B. Weight
C. neurons
D. axons
View Answer
Ans : A
Explanation: The output at each node is called its activation or node value.
(neural-networks-mcq-questions-ai)
Next »
Aakash Scholarship Exam

Exciting Rewards. All India Rank. Win a trip to NASA. Free MN
School Booster Course.
Ad Aakash BYJUS Sign Up
12/5/21, 10:47 PM 300+ TOP Neural Networks Multiple Choice Questions and Answers
HOME Interview Questions MCQs *LAB VIVA CLASS NOTES SEMINAR TOPICS
ONLINE TEST GATE CAT Internship ABOUT US Privacy Policy
Any Skill Sear
Home » Neural Networks Objective Questions » 300+ TOP

Neural Networks Multiple Choice Questions and Answers
300+ TOP Neural Networks

Multiple Choice Questions and
Answers
Ads by
Stop seeing this ad Why this ad?
Online Machine Learning
Compare courses in one easy search from multiple p
Coursary
https://engineeringinterviewquestions.com/neural-networks-multiple-choice-questions-and-answers/ 1/68
Neural Networks Multiple Choice Questions :-

1. A 3-input neuron is trained to output a zero when the
input is 110 and a one when the input is 111. After
generalization, the output will be zero when and only when
the input is:
a) 000 or 110 or 011 or 101
b) 010 or 100 or 110 or 101
c) 000 or 010 or 110 or 100
d) 100 or 111 or 101 or 001
Answer: c
Explanation: The truth table before generalization is:
Inputs Output
000 $
001 $
010 $
011 $
100 $
101 $
110 0
111 1
where $ represents don’t know cases and the output is random.
After generalization, the truth table becomes:
Inputs Output
000 0
001 1
010 0
011 1
100 0
101 1
110 0
111 1
2. A perceptron is:
a) a single layer feed-forward neural network with pre-processing
b) an auto-associative neural network
c) a double layer auto-associative neural network
d) a neural network that contains feedback
Answer: a
Explanation: The perceptron is a single layer feed-forward neural

network. It is not an auto-associative network because it has no
feedback and is not a multiple layer neural network because the pre-
processing stage is not made of neurons.
3. An auto-associative network is:
a) a neural network that contains no loops
b) a neural network that contains feedback
c) a neural network that has only one loop
d) a single layer feed-forward neural network with pre-processing
Answer: b
Explanation: An auto-associative network is equivalent to a neural

network that contains feedback. The number of feedback paths(loops)
does not have to be one.
4. A 4-input neuron has weights 1, 2, 3 and 4. The transfer

function is linear with the constant of proportionality being
equal to 2. The inputs are 4, 10, 5 and 20 respectively. The

output will be:
a) 238
b) 76
c) 119
d) 123
Answer: a
Explanation: The output is found by multiplying the weights with

their respective inputs, summing the results and multiplying with the
transfer function. Therefore:
Output = 2 * (1*4 + 2*10 + 3*5 + 4*20) = 238.
5. Which of the following is true?
(i) On average, neural networks have higher computational

rates than conventional computers.
(ii) Neural networks learn by example.
(iii) Neural networks mimic the way the human brain

works.
a) All of the mentioned are true
b) (ii) and (iii) are true
c) (i), (ii) and (iii) are true
Answer: a
Explanation: Neural networks have higher computational rates than

conventional computers because a lot of the operation is done in
parallel. That is not the case when the neural network is simulated on
a computer. The idea behind neural nets is based on the way the
human brain works. Neural nets cannot be programmed, they cam
only learn by examples.
6. Which of the following is true for neural networks?
(i) The training time depends on the size of the network.
(ii) Neural networks can be simulated on a conventional

computer.
(iii) Artificial neurons are identical in operation to

biological ones.
a) All of the mentioned
b) (ii) is true
c) (i) and (ii) are true
Answer: c
Explanation: The training time depends on the size of the network;

the number of neuron is greater and therefore the number of possible
‘states’ is increased. Neural networks can be simulated on a
conventional computer but the main advantage of neural networks –
parallel execution – is lost. Artificial neurons are not identical in
operation to the biological ones.
7. What are the advantages of neural networks over

conventional computers?
(i) They have the ability to learn by example
(ii) They are more fault tolerant
(iii)They are more suited for real time operation due to

their high ‘computational’ rates
a) (i) and (ii) are true
b) (i) and (iii) are true
c) Only (i)
d) All of the mentioned
Answer: d
Explanation: Neural networks learn by example. They are more fault

tolerant because they are always able to respond and small changes in
input do not normally cause a change in output. Because of their
parallel architecture, high computational rates are achieved.
8. Which of the following is true?
Single layer associative neural networks do not have the

ability to:
(i) perform pattern recognition
(ii) find the parity of a picture
(iii)determine whether two or more shapes in a picture are connected

or not
a) (ii) and (iii) are true
b) (ii) is true
c) All of the mentioned
Answer: a
Explanation: Pattern recognition is what single layer neural networks

are best at but they don’t have the ability to find the parity of a picture
or to determine whether two shapes are connected or not.
9. Which is true for neural networks?
a) It has set of nodes and connections
b) Each node computes it’s weighted input
c) Node could be in excited state or non-excited state
Answer: d
Explanation: All mentioned are the characteristics of neural network.
10. Neuro software is:
a) A software used to analyze neurons
b) It is powerful and easy neural network
c) Designed to aid experts in real world
d) It is software used by Neuro surgeon
Answer: b
11. Why is the XOR problem exceptionally interesting to

neural network researchers?
a) Because it can be expressed in a way that allows you to use a neural

network
b) Because it is complex binary operation that cannot be solved using

neural networks
c) Because it can be solved by a single layer perceptron
d) Because it is the simplest linearly inseparable problem that exists.
Answer: d
12. What is back propagation?
a) It is another name given to the curvy function in the perceptron
b) It is the transmission of error back through the network to adjust

the inputs
c) It is the transmission of error back through the network to allow

weights to be adjusted so that the network can learn.
Answer: c
Explanation: Back propagation is the transmission of error back

through the network to allow weights to be adjusted so that the
network can learn.
13. Why are linearly separable problems of interest of

neural network researchers?
a) Because they are the only class of problem that network can solve
successfully
b) Because they are the only class of problem that Perceptron can
solve successfully
c) Because they are the only mathematical functions that are continue
d) Because they are the only mathematical functions you can draw
Answer: b
Explanation: Linearly separable problems of interest of neural

network researchers because they are the only class of problem that
Perceptron can solve successfully
14. Which of the following is not the promise of artificial

neural network?
a) It can explain result
b) It can survive the failure of some nodes
c) It has inherent parallelism
d) It can handle noise
Answer: a
Explanation: The artificial Neural Network (ANN) cannot explain

result.
15. Neural Networks are complex ______________ with

many parameters.
a) Linear Functions
b) Nonlinear Functions
c) Discrete Functions
d) Exponential Functions
Answer: a
Explanation: Neural networks are complex linear functions with many

parameters.
16. A perceptron adds up all the weighted inputs it receives,

and if it exceeds a certain value, it outputs a 1, otherwise it
just outputs a 0.
a) True
b) False
c) Sometimes – it can also output intermediate values as well
d) Can’t say
Answer: a
Explanation: Yes the perceptron works like that.
17. The name for the function in question 16 is
a) Step function
b) Heaviside function
c) Logistic function
d) Perceptron function
Answer: b
Explanation: Also known as the step function – so answer 1 is also
right. It is a hard thresholding function, either on or off with no in-

between.
18. Having multiple perceptrons can actually solve the XOR

problem satisfactorily: this is because each perceptron can
partition off a linear part of the space itself, and they can
then combine their results.
a) True – this works always, and these multiple perceptrons learn to

classify even complex problems.
b) False – perceptrons are mathematically incapable of solving

linearly inseparable functions, no matter what you do
c) True – perceptrons can do this but are unable to learn to do it –

they have to be explicitly hand-coded
d) False – just having a single perceptron is enough
Answer: c
19. The network that involves backward links from output

to the input and hidden layers is called as ____.
a) Self organizing maps
b) Perceptrons
c) Recurrent neural network
d) Multi layered perceptron
Answer: c
Explanation: RNN (Recurrent neural network) topology involves

backward links from output to the input and hidden layers.
20. Which of the following is an application of NN (Neural

Network)?
a) Sales forecasting
b) Data validation
c) Risk management
Answer: d
Explanation: All mentioned options are applications of Neural

Network.
21. Different learning method does not include:
a) Memorization
b) Analogy
c) Deduction
d) Introduction
Answer: d
Explanation: Different learning methods include memorization,

analogy and deduction.
22. Following are the advantage/s of Decision Trees. Choose

that apply.
a) Possible Scenarios can be added
b) For data including categorical variables with different number of

levels, information gain in decision trees are biased in favor of those
attributes with more levels
c) Worst, best and expected values can be determined for different

scenarios
d) Use a white box model, If given result is provided by a model
Answer: a, c, d
23. Which of the following is the model used for learning?
a) Decision trees
b) Neural networks
c) Propositional and FOL rules
Answer: d
Explanation: Decision tress, Neural networks, Propositional rules and

FOL rules all are the models of learning.
24. Automated vehicle is an example of ______.
a) Supervised learning
b) Unsupervised learning
c) Active learning
d) Reinforcement learning
Answer: a
Explanation: In automatic vehicle set of vision inputs and

corresponding actions are available to learner hence it’s an example of
supervised learning.
25. Following is an example of active learning:
a) News recommendation system
b) Dust cleaning machine
c) Automated vehicle
Answer: a
Explanation: In active learning, not only the teacher is available but

the learner can ask suitable perception-action pair example to
improve performance.
26. In which of the following learning the teacher returns

reward and punishment to learner?
a) Active learning
b) Reinforcement learning
c) Supervised learning
d) Unsupervised learning
Answer: b
Explanation: Reinforcement learning is the type of learning in which

teacher returns award or punishment to learner.
27. Decision trees are appropriate for the problems where:
a) Attributes are both numeric and nominal
b) Target function takes on a discrete number of values.
c) Data may have errors
Answer: d
Explanation: Decision trees can be used in all the conditions stated.
28. Which of the following is not an application of learning?
a) Data mining
b) WWW
c) Speech recognition
Answer: d
Explanation: All mentioned options are applications of learning.
29. Which of the following is the component of learning

system?
a) Goal
b) Model
c) Learning rules
Answer: d
Explanation: Goal, model, learning rules and experience are the

components of learning system.
30. Following is also called as exploratory learning:
b) Active learning
c) Unsupervised learning
Answer: c
Explanation: In unsupervised learning no teacher is available hence it

is also called unsupervised learning.
31. A _________ is a decision support tool that uses a tree-

like graph or model of decisions and their possible
consequences, including chance event outcomes, resource
costs, and utility.
a) Decision tree
b) Graphs
c) Trees
d) Neural Networks
Answer: a
Explanation: Refer the definition of Decision tree.
32. Decision Tree is a display of an algorithm.
a) True
b) False
Answer: a
33. Decision Tree is
a) Flow-Chart
b) Structure in which internal node represents test on an attribute,

each branch represents outcome of test and each leaf node represents
class label
c) Both a) & b)
Answer: c
Explanation: Refer the definition of Decision tree.
34. Decision Trees can be used for Classification Tasks.
a) True
b) False
Answer: a
35. How many types of learning are available in machine

learning?
a) 1
b) 2
c) 3
d) 4
Answer: c
Explanation: The three types of machine learning are supervised,

unsupervised and reinforcement.
36. Choose from the following that are Decision Tree nodes
a) Decision Nodes
b) Weighted Nodes
c) Chance Nodes
d) End Nodes
Answer: a, c, d
37. Decision Nodes are represented by,
a) Disks
b) Squares
c) Circles
d) Triangles
Answer: b
38. Chance Nodes are represented by,
a) Disks
b) Squares
c) Circles
d) Triangles
Answer: c
39. End Nodes are represented by,
a) Disks
b) Squares
c) Circles
d) Triangles
Answer: d
40. How the decision tree reaches its decision?
a) Single test
b) Two test
c) Sequence of test
d) No test
Answer: c
Explanation: A decision tree reaches its decision by performing a

sequence of tests.
41. What will take place as the agent observes its

interactions with the world?
a) Learning
b) Hearing
c) Perceiving
d) Speech
Answer:a
Explanation:Learning will take place as the agent observes its

interactions with the world and its own decision making process.
42. Which modifies the performance element so that it

makes better decision?
a) Performance element
b) Changing element
c) Learning element
Answer:c
Explanation:A learning element modifies the performance element so

that it can make better decision.
43. How many things are concerned in design of a learning

element?
a) 1
b) 2
c) 3
d) 4
Answer:c
Explanation:The three main issues are affected in design of a learning

element are components, feedback and representation.
44. What is used in determining the nature of the learning

problem?
a) Environment
b) Feedback
c) Problem
Answer:b
Explanation:The type of feedback is used in determining the nature of

the learning problem that the agent faces.
45. How many types are available in machine learning?
a) 1
b) 2
c) 3
d) 4
Answer:c
Explanation:The three types of machine learning are supervised,

46. Which is used for utility functions in game playing

algorithm?
a) Linear polynomial
b) Weighted polynomial
c) Polynomial
d) Linear weighted polynomial
Answer:d
Explanation:Linear weighted polynomial is used for learning element

in the game playing programs.
47. Which is used to choose among multiple consistent

hypotheses?
a) Razor
b) Ockham razor
c) Learning element
Answer:b
Explanation:Ockham razor prefers the simplest hypothesis consistent

with the data intuitively.
48. What will happen if the hypothesis space contains the

true function?
a) Relizable
b) Unrelizable
c) Both a & b
Answer:b
Explanation:A learning problem is realizable if the hypothesis space

contains the true function.
49. What takes input as an object described bya set of

attributes?
a) Tree
b) Graph
c) Decision graph
d) Decision tree
Answer:d
Explanation:Decision tree takes input as an object described by a set

of attributes and returns a decision.
a) Single test
b) Two test
c) Sequence of test
d) No test
Answer:c
Explanation:A decision tree reaches its decision by performing a

sequence of tests.
51. What will take place as the agent observes its interactions with the
world?
a) Learning
b) Hearing
c) Perceiving
d) Speech
Answer: a
Explanation: Learning will take place as the agent observes its

interactions with the world and its own decision making process.
52. Which modifies the performance element so that it makes better

decision?
a) Performance element
b) Changing element
c) Learning element
Answer: c
Explanation: A learning element modifies the performance element so

that it can make better decision.
53. How many things are concerned in design of a learning element?
a) 1
b) 2
c) 3
d) 4
Answer: c
Explanation: The three main issues are affected in design of a learning

element are components, feedback and representation.
54. What is used in determining the nature of the learning problem?
a) Environment
b) Feedback
c) Problem
Answer: b
Explanation: The type of feedback is used in determining the nature of

the learning problem that the agent faces.
a) 1
b) 2
c) 3
d) 4
Answer: c
Explanation: The three types of machine learning are supervised,

56. Which is used for utility functions in game playing algorithm?
a) Linear polynomial
b) Weighted polynomial
c) Polynomial
d) Linear weighted polynomial
Answer: d
Explanation: Linear weighted polynomial is used for learning element

in the game playing programs.
57. Which is used to choose among multiple consistent hypotheses?
a) Razor
b) Ockham razor
c) Learning element
Answer: b
Explanation: Ockham razor prefers the simplest hypothesis consistent

with the data intuitively.
58. What will happen if the hypothesis space contains the true
function?
a) Realizable
b) Unrealizable
c) Both a & b
Answer: b
Explanation: A learning problem is realizable if the hypothesis space

contains the true function.
59. What takes input as an object described by a set of attributes?
a) Tree
b) Graph
c) Decision graph
d) Decision tree
Answer: d
Explanation: Decision tree takes input as an object described by a set

of attributes and returns a decision.
a) Single test
b) Two test
c) Sequence of test
d) No test
Answer: c
Explanation: A decision tree reaches its decision by performing a

sequence of tests.
61. Factors which affect the performance of learner system does not
include
a) Representation scheme used
b) Training scenario
c) Type of feedback
d) Good data structures
Answer: d
Explanation: Factors which affect the performance of learner system

does not include good data structures.
a) Memorization
b) Analogy
c) Deduction
d) Introduction
Answer: d
Explanation: Different learning methods include memorization,

analogy and deduction.
a) Decision trees
b) Neural networks
c) Propositional and FOL rules
Answer: d
Explanation: Decision trees, Neural networks, Propositional rules and

FOL rules all are the models of learning.
b) Unsupervised learning
c) Active learning
Answer: a
Explanation: In automatic vehicle set of vision inputs and

corresponding actions are available to learner hence it’s an example of
supervised learning.
a) News Recommender system
b) Dust cleaning machine
c) Automated vehicle
Answer: a
Explanation: In active learning, not only the teacher is available but

the learner can ask suitable perception-action pair example to
improve performance.
66. In which of the following learning the teacher returns reward and
punishment to learner?
a) Active learning
b) Reinforcement learning
c) Supervised learning
d) Unsupervised learning
Answer: b
Explanation: Reinforcement learning is the type of learning in which

teacher returns award or punishment to learner.
a) Attributes are both numeric and nominal
b) Target function takes on a discrete number of values.
c) Data may have errors
Answer: d
Explanation: Decision trees can be used in all the conditions stated.
a) Data mining
b) WWW
c) Speech recognition
Answer: d
Explanation: All mentioned options are applications of learning.
69. Which of the following is the component of learning system?
a) Goal
b) Model
c) Learning rules
Answer: d
Explanation: Goal, model, learning rules and experience are the

components of learning system.
b) Active learning
c) Unsupervised learning
Answer: c
Explanation: In unsupervised learning no teacher is available hence it

is also called unsupervised learning.
71. Which is not a desirable property of a logical rule-based system?
a) Locality
b) Attachment
c) Detachment
d) Truth-Functionality
e) Global attribute
Answer: b
Explanation: Locality: In logical systems, whenever we have a rule of
the form A => B, we can conclude B, given evidence A, without

worrying about any other rules. Detachment: Once a logical proof is
found for a proposition B, the proposition can be used regardless of
how it was derived .That is, it can be detachment from its justification.
Truth-functionality: In logic, the truth of complex sentences can be
computed from the truth of the components. However, there are no
Attachment properties lies in a Rule-based system. Global attribute
defines a particular problem space as user specific and changes
according to user’s plan to problem.
72. How is Fuzzy Logic different from conventional control methods?
a) IF and THEN Approach
b) FOR Approach
c) WHILE Approach
d) DO Approach
e) Else If approach
Answer: a
Explanation: FL incorporates a simple, rule-based IF X AND Y THEN

Z approach to a solving control problem rather than attempting to
model a system mathematically.
73. In an Unsupervised learning
a) Specific output values are given
b) Specific output values are not given
c) No specific Inputs are given
d) Both inputs and outputs are given
e) Neither inputs nor outputs are given
Answer: b
Explanation: The problem of unsupervised learning involves learning

patterns in the input when no specific output values are supplied. We
cannot expect the specific output to test your result. Here the agent
does not know what to do, as he is not aware of the fact what propose
system will come out. We can say an ambiguous un-proposed
situation.
74. Inductive learning involves finding a
a) Consistent Hypothesis
b) Inconsistent Hypothesis
c) Regular Hypothesis
d) Irregular Hypothesis
e) Estimated Hypothesis
Answer: a
Explanation: Inductive learning involves finding a consistent

hypothesis that agrees with examples. The difficulty of the task
depends on the chosen representation.
75. Computational learning theory analyzes the sample complexity

and computational complexity of
a) Unsupervised Learning
b) Inductive learning
c) Forced based learning
d) Weak learning
e) Knowledge based learning
Answer: b
Explanation: Computational learning theory analyzes the sample

complexity and computational complexity of inductive learning. There
is a tradeoff between the expressiveness of the hypothesis language
and the ease of learning.
76. If a hypothesis says it should be positive, but in fact, it is negative,

we call it
a) A consistent hypothesis
b) A false negative hypothesis
c) A false positive hypothesis
d) A specialized hypothesis
e) A true positive hypothesis
Answer: c
Explanation: Consistent hypothesis go with examples, If the

hypothesis says it should be negative but infect it is positive, it is false
negative. If a hypothesis says it should be positive, but in fact, it is
negative, it is false positive. In a specialized hypothesis we need to
have certain restrict or special conditions.
77. Neural Networks are complex ———————–with many

parameters.
a) Linear Functions
b) Nonlinear Functions
c) Discrete Functions
d) Exponential Functions
e) Power Functions
Answer: b
Explanation: Neural networks parameters can be learned from noisy

data and they have been used for thousands of applications, so it
varies from problem to problem and thus use nonlinear functions.
78. A perceptron is a ——————————–.
a) Feed-forward neural network
b) Back-propagation algorithm
c) Back-tracking algorithm
d) Feed Forward-backward algorithm
e) Optimal algorithm with Dynamic programming
Answer: a
Explanation: A perceptron is a Feed-forward neural network with no

hidden units that can be representing only linear separable functions.
If the data are linearly separable, a simple weight updated rule can be
used to fit the data exactly.
79. Which of the following statement is true?
a) Not all formal languages are context-free
b) All formal languages are Context free
c) All formal languages are like natural language
d) Natural languages are context-oriented free
e) Natural language is formal
Answer: a
Explanation: Not all formal languages are context-free.
80. Which of the following statement is not true?
a) The union and concatenation of two context-free languages is

context-free
b) The reverse of a context-free language is context-free, but the

complement need not be
c) Every regular language is context-free because it can be described

by a regular grammar
d) The intersection of a context-free language and a regular language
is always context-free
e) The intersection two context-free languages is context-free
Answer: e
Explanation: The union and concatenation of two context-free

languages is context-free; but intersection need not be.
81. The process by which you become aware of messages through your
sense is called
a) Organization
b) Sensation
c) Interpretation-Evaluation
d) Perception
Answer: d
82. Susan is so beautiful; I bet she is smart too. This is an example of
a) The halo effect
b) The primary effect
c) A self-fulfilling prophecy
d) The recency effect
Answer: a
83. _____ prevents you from seeing an individual as an individual

rather than as a member of a group.
a) Cultural mores
b) Stereotypes
c) Schematas
d) Attributions
Answer: c
84. When you get fired from your job and you determine it is because
your boss dislikes you, you are most likely exhibiting
a) Self-promotion
b) Fundamental attribution error
c) Over-attribution
d) Self-serving bias
Answer: d
85. Mindless processing is
a) careful, critical thinking
b) inaccurate and faulty processing
c) information processing that relies heavily on familiar schemata
d) processing that focuses on unusual or novel events
Answer: c
86. What kind of perception is used in printing?
a) Optical character recognition
b) Speech recognition
c) Perception
Answer: a
Explanation: In When perception is used in printing means, It is

called as optical character recognition.
87. Selective retention occurs when
a) we process, store, and retrieve information that we have already

selected, organized, and interpreted
b) we make choices to experience particular stimuli
c) we make choices to avoid particular stimuli
d) we focus on specific stimuli while ignoring other stimuli
Answer: a
88. Which of the following strategies would NOT be effective at

improving your communication competence?
a) Recognize the people, objects, and situations remain stable over

time
b) Recognize that each person’s frame of perception is unique
c) Be active in perceiving
d) Distinguish facts from inference
Answer: a
89. _____________ is measured by the number of mental

structures we use, how abstract they are, and how elaborate they
interact to shape our perceptions.
a) intrapersonal structure
b) perceptual set
c) self-justification
d) None of the above
Answer: d
90. A perception check is
a) a cognitive bias that makes us listen only to information we already

agree with.
b) a method teachers use to reward good listeners in the classroom.
c) any factor that gets in the way of good listening and decreases our
ability to interpret correctly.
d) a response that allows you to state your interpretation and ask your
partner whether or not that interpretation is correct.
Answer: d
91. Which provides agents with information about the world they
inhabit?
a) Sense
b) Perception
c) Reading
d) Hearing
Answer: b
Explanation: Perception provides agents with information about the

world they inhabit.
92. What is used to initiate the perception in the environment?
a) Sensor
b) Read
c) Actuators
Answer: a
Explanation: A sensor is anything that can record some aspect of the

environment.
93. What is the study of light?
a) Biology
b) Lightology
c) Photometry
Answer: c
94. How to increase the brightness of the pixel?
a) Sound
b) Amount of light
c) Surface
d) Waves
Answer: b
Explanation: The brightness of a pixel in the image is proportional to

the amount of light directed towards the camera.
95. How many kinds of reflection are available in image perception?
a) 1
b) 2
c) 3
d) 4
Answer: b
Explanation: There are two kinds of reflection. They are specular and
diffuse reflection.
96. What is meant by predicting the value of a state variable from the
past?
a) Specular reflection
b) Diffuse reflection
c) Gaussian filter
d) Smoothing
Answer: d
Explanation: Smoothing meant predicting the value of a state variable

from the past and by given evidence and calculating the present and
future.
97. How many types of image processing techniques are there in

image perception?
a) 1
b) 2
c) 3
d) 4
Answer: c
Explanation: The three image processing techniques are smoothing,

edge detection and image segmentation.
98. Which is meant by assuming any two neighboring that are both
edge pixels with consistent orientation?
a) Canny edge detection
b) Smoothing
c) Segmentation
Answer: a
Explanation: Canny edge detection is assuming any two neighboring

that are edge pixels with consistent orientation.
99. What is the process of breaking an image into groups?
a) Edge detection
b) Smoothing
c) Segmentation
Answer: c
Explanation: Segmentation is the process of breaking an image into
groups, based on the similarities of the pixels.
100. How many types of 3-D image processing techniques are there in
image perception?
a) 3
b) 4
c) 5
d) 6
Answer: c
Explanation: The five types of 3-D image processing techniques are

motion, binocular stereopsis, texture, shading and contour.
Neural Networks Objective Questions and Answers Pdf

101. Which condition is used to cease the growth of forward chaining?
a) Atomic sentences
b) Complex sentences
c) No further inference
Answer:c
Explanation:Forward chain can grow by adding new atomic sentences

until no further inference is made.
102. Which closely resembles propositional definite clause?
a) Resolution
b) Inference
c) Conjuction
d) First-order definite clauses
Answer:d
Explanation:Because they are disjunction of literals of which exactly

one is positive.
103. What is the condition of variables in first-order literals?
a) Existentially quantified
b) Universally quantified
c) Both a & b
Answer:b
Explanation:First-order literals will accept variables only if they are

universally quantified.
104. Which are more suitable normal form to be used with definite
clause?
a) Positive literal
b) Negative literal
c) Generalized modus ponens
d) Neutral literal
Answer:c
Explanation:Definite clauses are a suitable normal form for use with

generalized modus ponen.
105. Which will be the instance of the class datalog knowledge bases?
a) Variables
b) No function symbols
c) First-order definite clauses
Answer:b
Explanation:If the knowledge base contains no function symbols

means, it is an instance of the class datalog knowledge base.
106. Which knowledge base is called as fixed point?
a) First-order definite clause are similar to propositional forward

chaining
b) First-order definite clause are mismatch to propositional forward

chaining
c) Both a & b
Answer:a
Explanation:Fixed point reached by forward chaining with first-order

definiteclause are similar to those for propositional forward chaining.
107. How to eliminate the redundant rule matching attempts in the

forward
chaining?
a) Decremental forward chaining
b) Incremental forward chaining
c) Data complexity
Answer:b
Explanation:We can eliminate the redundant rule matching attempts

in the forward chaining by using incremental forward chaining.
108. From where did the new fact inferred on new iteration is derived?
a) Old fact
b) Narrow fact
c) New fact
Answer:c
109. Which will solve the conjuncts of the rule so that the total cost is
minimized?
a) Constraint variable
b) Conjunct ordering
c) Data complexity
Answer:b
Explanation:Conjunct ordering will find an ordering to solve the

conjuncts of the rule premise so that the total cost is minimized.
110. How many possible sources of complexity are there in forward

chaining?
a) 1
b) 2
c) 3
d) 4
Answer:c
Explanation:The three possible sources of complexity are inner loop,

algorithm rechecks every rule on every iteration, algorithm might
generate many facts irrelevant to the goal.
111. Which algorithm will work backward from the goal to solve a
problem?
a) Forward chaining
b) Backward chaining
c) Hill-climb algorithm
Answer:b
Explanation:Backward chaining algorithm will work backward from

the goal and it will chain the known facts that support the proof.
112. Which is mainly used for automated reasoning?
a) Backward chaining
b) Forward chaining
c) Logic programming
d) Parallel programming
Answer:c
Explanation:Logic programming is mainly used to check the working
process of the system.
113. What will backward chaining algorithm will return?
a) Additional statements
b) Substitutes matching the query
c) Logical statement
Answer:b
Explanation:It will contains the list of goals containing a single

element and returns the set of all substitutions satisfying the query.
114. How can be the goal is thought of in backward chaining

algorithm?
a) Queue
b) List
c) Vector
d) Stack
Answer:d
Explanation:The goals can be thought of as stack and if all of them us

satisfied means, then current branch of proof succeeds.
115. What are used in backward chaining algorithm?
a) Conjucts
b) Substitution
c) Composition of substitution
Answer:c
116. Which algorithm are in more similar to backward chainiing

algorithm?
a) Depth-first search algorithm
b) Breadth-first search algorithm
c) Hill-climbing search algorithm
Answer:a
Explanation:It is depth-first search algorithm because its space

requirements are linear in the size of the proof.
117. Which problem can frequently occur in backward chaining

algorithm?
a) Repeated states
b) Incompleteness
c) Complexity
d) Both a & b
Answer:d
Explanation:If there is any loop in the chain means, It will lead to

incompleteness and repeated states.
118. How the logic programming can be constructed?
a) Variables
b) Expressing knowledge in a formal language
c) Graph
Answer:b
Explanation:Logic programming can be constructed by expressing

knowledge in a formal expression and the problem can be solved by
running inference process.
119. What form of negation does the prolog allows?
a) Negation as failure
b) Proposition
c) Substitution
d) Negation as success
Answer:a
120. Which is omitted in prolog unification algorithm?
a) Variable check
b) Occur check
c) Proposition check
d) Both b & c
Answer:b
Explanation:Occur check is omitted in prolog unification algorithm

because of unsound inferences.
121. How many issues are available in describing degree of belief?
a) 1
b) 2
c) 3
d) 4
Answer:b
Explanation:The main issues for degree of belief are nature of the

sentences and the dependance of degree of the belief.
122. What is used for probability theory sentences?
a) Conditional logic
b) Logic
c) Extension of propositional logic
Answer:c
Explanation:The version of probability theory we present uses an

extension of propositional logic for its sentences.
123. Where does the dependance of experience is reflected in prior

proability
sentences?
a) Syntactic distinction
b) Semantic distinction
c) Both a & b
Answer:a
Explanation:The dependance on experience is reflected in the

syntactic distinction between prior probability statements.
124. Where does the degree of belief are applied?
a) Propositions
b) Literals
c) Variables
d) Statements
Answer:a
125. How many formal languages are used for stating propositions?
a) 1
b) 2
c) 3
d) 4
Answer:b
Explanation:The two formal languages used for stating propositions

are propositional logic and first-order logic.
126. What is the basic element for a language?
a) Literal
b) Variable
c) Random variable
Answer:c
Explanation:The basic element for a langauage is the random variable,

which can be thought as a part of world and its status is initially
unknown.
127. How many types of random variables are available?
a) 1
b) 2
c) 3
d) 4
Answer:c
Explanation:The three types of random variables are boolean, discrete

and continuous.
128. Which is the complete specification of the state of the world?
a) Atomic event
b) Complex event
c) Simple event
Answer:a
Explanation:An atomic event is the complete specification of the state

of the world about which the event is uncertain.
129. Which variable cannot be written in entire distribution as a table?
a) Discrete
b) Continuous
c) Both a & b
Answer:b
Explanation:For continuous variables, it is not posible to write out the

entire distribution as a table.
130. What is meant by probability density function?
a) Probability distributions
b) Continuous variable
c) Discrete variable
d) Probability distributions for Continuous variables
Answer:d
131. Which is created by using single propositional symbol?
a) Complex sentences
b) Atomic sentences
c) Composition sentences
Answer:b
Explanation:Atomic sentences are indivisible syntactic elements

consisting of single propositional symbol.
132. Which is used to construct the complex sentences?
a) Symbols
b) Connectives
c) Logical connectives
Answer:c
133. How many proposition symbols are there in artificial

intelligence?
a) 1
b) 2
c) 3
d) 4
Answer:b
Explanation:The two proposition symbols are true and false.
134. How many logical connectives are there in artificial intelligence?
a) 2
b) 3
c) 4
d) 5
Answer:d
Explanation:The five logical symbols are negation, conjuction,

disjunction,implication and biconditional.
135. Which is used to compute the truth of any sentence?
a) Semantics of propositional logic
b) Alpha-beta pruning
c) First-order logic
d) Both a & b
Answer:a
Explanation:Because the meaning of the sentences is really needed to

compute the truth.
136. Which are needed to compute the logical inference algorithm?
a) Logical equivalence
b) Validity
c) Satisfiability
Answer:d
Explanation:Logical inference algorithm can be solved be using logical

equivalence, Validity and satisfiability.
137. From which rule does the modus ponens are derived?
a) Inference rule
b) Module rule
c) Both a & b
Answer:a
Explanation:Inference rule contains the standard pattern that leads to

desired goal. The best form of inference rule is modus ponens.
138. Which is also called single inference rule?
a) Reference
b) Resolution
c) Reform
Answer:b
Explanation:Because resolution yields a complete inference rule when

coupled with any search algorithm.
139. Which form is called as conjunction of disjunction of literals?
a) Conjunctive normal form
b) Disjunctive normal form
c) Normal form
Answer:a
140. What can be viewed as single leteral of disjunction?
a) Multiple clause
b) Combine clause
c) Unit clause
Answer:c
Explanation:A single literal can be viewed as a disjunction or one

literal also, called as unit clause.
141. Which is a refutation complete inference procedure for

propositional logic?
a) Clauses
b) Variables
c) Propositional resolution
d) Proposition
Answer: c
Explanation: Propositional resolution is a refutation complete

inference procedure for propositional logic.
142. What kind of clauses is available in Conjunctive Normal Form?
a) Disjunction of literals
b) Disjunction of variables
c) Conjunction of literals
d) Conjunction of variables
Answer: a
Explanation: First-order resolution requires the clause to be in

disjunction of literals in Conjunctive Normal Form.
143. What is the condition of literals in variables?
a) Existentially quantified
b) Universally quantified
c) Quantified
Answer: b
Explanation: Literals that contain variables are assumed to be

universally quantified.
144. Which can be converted to inferred equivalent CNF (Conjunction

Normal Form) sentence?
a) Every sentence of propositional logic
b) Every sentence of inference
c) Every sentence of first-order logic
Answer: c
Explanation: Every sentence of first-order logic can be converted to

inferred equivalent CNF(Conjunction Normal Form) sentence.
145. Which sentence will be unsatisfiable if the CNF (Conjunction

Normal Form) sentence is unsatisfiable?
a) Search statement
b) Reading statement
c) Replaced statement
d) Original statement
Answer: d
Explanation: The CNF statement will be unsatisfiable just when the

original sentence is unsatisfiable.
146. Which rule is equal to resolution rule of first-order clauses?
a) Propositional resolution rule
b) Inference rule
c) Resolution rule
Answer: a
Explanation: The resolution rule for first-order clauses is simply a

lifted version of the propositional resolution rule.
147. At which state does the propositional literals are complementary.
a) If one variable is less
b) If one is the negation of the other
c) Both a & b
Answer: b
Explanation: Propositional literals are complementary if one is the

negation of the other.
148. What is meant by factoring?
a) Removal of redundant variable
b) Removal of redundant literal
c) Addition of redundant literal
d) Addition of redundant variable
Answer: b
149. What will happen if two literals are identical?
a) Remains the same
b) Added as three
c) Reduced to one
Answer: c
Explanation: Propositional factoring reduces two literals to one if they

are identical.
150. When the resolution is called as refutation-complete?
a) Sentence is satisfiable
b) Sentence is unsatisfiable
c) Sentence remains the same
Answer: b
Explanation: Resolution is refutation-complete, if a set of sentence is
unsatisfiable, then resolution will always be able to derive a

contradiction.
151. Computers normally solve problem by breaking them down into a

series of yes-or-no decisions represented by 1s and 0s. What is the
name of the logic that allows computers to assign numerical values
that fail somewhere between 0 and 1?
a) Human logic
b) Fuzzy logic
c) Boolean logic
d) Operational logic
Answer: b
152. The component of an ICAI (Intelligent Computer-Asslsted

Instruction) presenting information to the student is the:
a) student model
b) problem-solving expertise
c) tutoring module
Answer: c
153. The company that grew out of research at the MIT AI lab is:
a) AI corp
b) LMI
c) Symbolics
d) both b & c
Answer: d
154. Which technique is being investigated as an approach to

automatic programming?
a) generative CAI
b) specification by example
c) All of the above
d) non-hierarchical planning
Answer: b
155. One definition of AI focuses on problem-solving methods that

process:
a) smell
b) symbols
c) touch
d) algorithms
Answer: b
156. Artificial intelligence is
a) the embodiment of human intellectual capabilities within a

computer.
b) a set of computer programs that produce output that would be

considered to reflect intelligence if it were generated by humans.
c) the study of mental faculties through the use of mental models

implemented on a computer.
Answer: d
157. The primary method that people use to sense their environment
is:
a) reading
b) writing
c) speaking
d) seeing
Answer: d
158. The Newell and Simon program that proved theorems of

Principia Mathematica was:
a) Elementary Perceiver
b) General Problem Solver
c) Logic Theorist
d) Boolean Algebra
Answer: c
159. In LISP, the function assigns . the value of a to b is
a) (setq a b)
b) (setq b a )
c) (b = a)
d) (set b = a)
Answer: b
160. The cray X-MP, IBM 3090 and connection machine can he
characterized as
a) SISD
b) SIMD
c) MISD
d) MIMD
Answer: b
161. Ambiguity may be caused by:
a) syntactic ambiguity
b) multiple word meanings
c) unclear antecedents
Answer: d
162. Which company offers the LISP machine considered to be “the

most powerful symbolic processor available”?
a) LMI
b) Symbolics
c) Xerox
d) Texas Instruments
Answer: b
163. What of the following is considered to be a pivotal event in the

history of Artificial Intelligence.
a) 1949, Donald O, The organization of Behavior,
b) 1950, Computing Machinery and Intelligence.
c) 1956, Dartmouth University Conference Organized by John

McCarthy
d) 1961, Computer and Computer Sense.
Answer: c
164. Natural language processing is divided into the two subfields of:
a) symbolic and numeric
b) time and motion
c) algorithmic and heuristic
d) understanding and generation
Answer: d
165. High-resolution, bit-mapped displays are useful for displaying:
a) clearer characters
b) graphics
c) more characters
Answer: d
166. A bidirectional feedback loop links computer modeling with:
a) artificial science
b) heuristic processing
c) human intelligence
d) cognitive science
Answer: d
167. Which of the following have people traditionally done better than
computers?
a) recognizing relative importance
b) finding similarities
c) resolving ambiguity
Answer: d
168. In LISP, the function evaluates both and is
a) set
b) setq
c) add
d) eva
Answer: a
169. What takes input as an object described bya set of attributes?
a) Tree
b) Graph
c) Decision graph
d) Decision tree
Answer: d
a) Single test
b) Two test
c) Sequence of test
d) No test
Answer: c
a) syntactic ambiguity
b) multiple word meanings
c) unclear antecedents
Answer: d
172. Which company offers the LISP machine considered “the most
powerful symbolic processor available”?
a) LMI
b) Symbolics
c) Xerox
d) Texas Instruments
Answer: b
173. What of the following is considered a pivotal event in the history

of Artificial Intelligence?
a) 1949, Donald O, The organization of Behavior
b) 1950, Computing Machinery and Intelligence

c) 1956, Dartmouth University Conference Organized by John
McCarthy
d) 1961, Computer and Computer Sense
Answer: c
174. Natural language processing is divided into the two sub-fields of:
a) symbolic and numeric
b) time and motion
c) algorithmic and heuristic
d) understanding and generation
Answer: c
175. High-resolution, bit-mapped displays are useful for displaying:
a) clearer characters
b) graphics
c) more characters
Answer: c
a) artificial science
b) heuristic processing
c) human intelligence
d) cognitive science
Answer: c
computers?
a) recognizing relative importance
b) finding similarities
c) resolving ambiguity
d) All of the above
Answer: c
a) set
b) setq
c) add
d) eva
Answer: a
179. Which type of actuator generates a good deal of power but tends
to be messy?
a) electric
b) hydraulic
c) pneumatic
d) Both b & c
Answer: b
180. Research scientists all over the world are taking steps towards
building computers with circuits patterned after the complex inter
connections existing among the human brain’s nerve cells. What name
is given to such type of computers?
a) Intelligent computers
b) Supercomputers
c) Neural network computers
d) Smart computers
Answer: c
181.Which search is equal to minimax search but eliminates the

branchesthat can’t influence the final decision?
a) Depth-first search
b) Breadth-first search
c) Alpha-beta pruning
Answer: c
182. Which values are independant in minimax search algorithm?
a) Pruned leaves x and y
b) Every states are dependant
c) Root is independant
Answer: a
183.To which depth does the alpha-beta pruning can be applied?
a) 10 states
b) 8 States
c) 6 States
d) Any depth
Answer: d
184.Which search is similar to minimax search?
a) Hill-climbing search
b) Depth-first search
c) Breadth-first search
Answer: b
185.Which value is assigned to alpha and beta in the alpha-beta

pruning?
a) Alpha = max
b) Beta = min
c) Beta = max
d) Both a & b
Answer: d
186.Where does the values of alpha-beta search get updated?
a) Along the path of search
b) Initial state itself
c) At the end
Answer: a
187.How the effectiveness of the alpha-beta pruning gets increased?
a) Depends on the nodes
b) Depends on the order in which they are executed
c) Both a & b
Answer: a
188.What is called as transposition table?
a) Hash table of next seen positions
b) Hash table of previously seen positions
c) Next value in the search
Answer: b
189.Which is identical to the closed list in Graph search?
a) Hill climbing search algorithm
b) Depth-first search
c) Transposition table
Answer: c
190.Which function is used to calculate the feasibility of whole game

tree?
a) Evaluation function
b) Transposition
c) Alpha-beta pruning
Answer: a
191.What is the action of task environment in artificial intelligence?
a) Problem
b) Solution
c) Agent
d) Observation
Answer: a
192.What is the expansion if PEAS in task environment?
a) Peer, Environment, Actuators, Sense
b) Perceiving, Enivornment, Actuators, Sensors
c) Performance, Environment, Actuators, Sensors,
Answer: c
193.What kind of observing environments are present in artificial

intelligence?
a) Partial
b) Fully
c) Learning
d) Both a & b
Answer: d
194.What kind of environment is strategic in artificial intelligence?
a) Deterministic
b) Rational
c) Partial
d) Stochastic
Answer: a
195.What kind of environment is crossword puzzle?
a) Static
b) Dynamic
c) Semidynamic
Answer: a
196.What kind of behavior does the stochastic environment posses?
a) Local
b) Deterministic
c) Ratioanl
d) Primary
Answer: a
197.Which is used to select the particular environment to run the

agent?
a) Environment creator
b) Environment Generator
c) Both a & b
Answer: b
198.Which environment is called as semidynamic?
a) Environment does not change with the passage of time
b) Agent performance changes
c) Environment will be changed
d) Both a & b
Answer: d
199.Where does the performance measure is included?
a) Rational agent
b) Task environment
c) Actuators
d) Sensor
Answer: b
200.Which is used to provide the feedback to the learning element?
a) Critic
b) Actuators
c) Sensor
Answer: a
201.Given a stream of text, Named Entity Recognition determines

which pronoun maps to which noun.
a) False
b) True
Answer: a
202.Natural Language generation is the main task of Natural language

processing.
a) True
b) False
Answer: a
203.OCR (Optical Character Recognition) uses NLP.
a) True
b) False
Answer: a
204.Parts-of-Speech tagging determines
a) part-of-speech for each word
b) part-of-speech for each word dynamically as per sentence structure

and meaning
c) all part-of-speech for a specific word given as input
Answer: b, c
205.Parsing determines Parse Trees (Grammatical Analysis) for a

given sentence.
a) True
b) False
Answer: a
206.IR (information Retrieval) and IE (Information Extraction) are

the two same thing.
a) True
b) False
Answer: b
207.Many words have more than one meaning; we have to select the
meaning which makes the most sense in context. This can be resolved
by
a) Fuzzy Logic
b) Word Sense Disambiguation
c) Shallow Semantic Analysis
Answer: b
208.Given a sound clip of a person or people speaking, determine the

textual representation of the speech.
a) Text-to-speech
b) Speech-to-text
Answer: b
209.Speech Segmentation is a subtask of Speech Recognition.
a) True
b) False
Answer: a
210. In linguistic morphology, _____________ is the process for

reducing inflected words to their root form.
a) Rooting
b) Stemming
c) Text-Proofing
d) Both a & b
Answer: b
Neural Networks Mcqs Pdf Download
---- >> Related Posts Of Above Questions :::
------>>[MOST IMPORTANT]<<------
Neural Network MCQs [set-6]
126. Which value is assigned to alpha and beta in the alpha-beta pruning?
A. alpha = max
B. beta = min
C. beta = max
D. both a & b
o m
.c
Answer: D
te
a
M
127. Where does the values of alpha-beta search get updated?
q
A. along the path of search c
B. initial state itself
M
C. at the end
D. none of the mentioned
Answer: A
128. How the effectiveness of the alpha-beta pruning gets increased?
A. depends on the nodes
B. depends on the order in which they are executed
C. both a & b
Answer: A
129. What is called as transposition table?
A. hash table of next seen positions
B. hash table of previously seen positions
Download more at McqMate.com

C. next value in the search
Answer: B
130. Which is identical to the closed list in Graph search?
A. hill climbing search algorithm
B. depth-first search
C. transposition table
o m
.c
te
Answer: C
a
q M
131. Which function is used to calculate the feasibility of whole game tree?
c
A. evaluation function M
B. transposition
C. alpha-beta pruning
D. all of the mentioned
Answer: A
132. What is the action of task environment in artificial intelligence?
A. problem
B. solution
C. agent
D. observation
Answer: A
133. What is the expansion if PEAS in task environment?
A. peer, environment, actuators, sense

B. perceiving, enivornment, actuators, sensors
C. performance, environment, actuators, sensors,
Answer: C
134. What kind of observing environments are present in artificial

intelligence?
A. partial
o m
B. fully
.c
C. learning
te
a
D. both a & b
q M
Answer: D
c
M
135. What kind of environment is strategic in artificial intelligence?
A. deterministic
B. rational
C. partial
D. stochastic
Answer: A
136. What kind of environment is crossword puzzle?
A. static
B. dynamic
C. semidynamic
Answer: A
137. What kind of behavior does the stochastic environment posses?

A. local
B. deterministic
C. ratioanl
D. primary
Answer: A
138. Which is used to select the particular environment to run the agent?
A. environment creator
o m
B. environment generator
.c
te
C. both a & b
a
q M
Answer: B
c
M
139. Which environment is called as semidynamic?
A. environment does not change with the passage of time
B. agent performance changes
C. environment will be changed
D. both a & b
Answer: D
140. Where does the performance measure is included?
A. rational agent
B. task environment
C. actuators
D. sensor
Answer: B

141. Which is used to provide the feedback to the learning element?
A. critic
B. actuators
C. sensor
Answer: A
142. Parts-of-Speech tagging determines o m

.c
A. part-of-speech for each word
te
a
M
B. part-of-speech for each word dynamically as per sentence structure and meaning
q
c
C. all part-of-speech for a specific word given as input

M
Answer: C
143. Many words have more than one meaning; we have to select the
meaning which makes the most sense in context. This can be resolved by
A. fuzzy logic
B. word sense disambiguation
C. shallow semantic analysis
Answer: B
144. In linguistic morphology, _____________ is the process for reducing

inflected words to their root form.
A. rooting
B. stemming
C. text-proofing

D. both a & b
Answer: B
o m
.c
te
a
q M
c
M

Take Quick Mock/Practice test on this topic HERE
For Discussion / Reporting / Correction of any MCQ please visit discussion page by clicking on
'answer' of respective MCQ.
o m
.c
te
a
q M
c
M

101. The company that grew out of research at the MIT AI lab is:
A. ai corp
B. lmi
C. symbolics
D. both b & c
o m
.c
Answer: D
te
a
programming? q M
102. Which technique is being investigated as an approach to automatic
c
A. generative cai M
B. specification by example
C. all of the above
D. non-hierarchical planning
Answer: B
103. One definition of AI focuses on problem-solving methods that

process:
A. smell
B. symbols
C. touch
D. algorithms
Answer: B
104. Artificial intelligence is
A. the embodiment of human intellectual capabilities within a computer.

B. a set of computer programs that produce output that would be considered to reflect intelligence
if it were generated by humans.
C. the study of mental faculties through the use of mental models implemented on a computer.
Answer: D
105. The primary method that people use to sense their environment is:
A. reading
o m
B. writing
.c
C. speaking
te
D. seeing a
Answer: D
q M
c
M
106. The Newell and Simon program that proved theorems of Principia
Mathematica was:
A. elementary perceiver
B. general problem solver
C. logic theorist
D. boolean algebra
Answer: C
107. In LISP, the function assigns . the value of a to b is
A. (setq a b)
B. (setq b a )
C. (b = a)
D. (set b = a)
Answer: B
108. The cray X-MP, IBM 3090 and connection machine can he

characterized as
A. sisd
B. simd
C. misd
D. mimd
Answer: B

o m
A. syntactic ambiguity
.c
te
B. multiple word meanings
a
C. unclear antecedents
q M
c
Answer: D M
110. Which company offers the LISP machine considered to be “the most
A. lmi
B. symbolics
C. xerox
D. texas instruments
Answer: B
111. What of the following is considered to be a pivotal event in the history

of Artificial Intelligence.
A. 1949, donald o, the organization of behavior,
B. 1950, computing machinery and intelligence.
C. 1956, dartmouth university conference organized by john mccarthy
D. 1961, computer and computer sense.
Answer: C

112. Natural language processing is divided into the two subfields of:
A. symbolic and numeric
B. time and motion
C. algorithmic and heuristic
D. understanding and generation
Answer: D
113. High-resolution, bit-mapped displays areo

m
.c useful for displaying:
e
A. clearer characters
at
B. graphics
q M
C. more characters
c
D. all of the mentioned M
Answer: D
A. artificial science
B. heuristic processing
C. human intelligence
D. cognitive science
Answer: D
A. set
B. setq
C. add
D. eva
Answer: A

116. Which company offers the LISP machine considered “the most
A. lmi
B. symbolics
C. xerox
D. texas instruments
Answer: B
o m
.c
e
117. What of the following is considered a pivotal event in the history of
t
Artificial Intelligence?
a
q M
A. 1949, donald o, the organization of behavior
c
B. 1950, computing machinery and intelligence
M
C. 1956, dartmouth university conference organized by john mccarthy
D. 1961, computer and computer sense
Answer: C
118. Natural language processing is divided into the two sub-fields of:
A. symbolic and numeric
B. time and motion
C. algorithmic and heuristic
D. understanding and generation
Answer: C
computers?
A. recognizing relative importance
B. finding similarities

C. resolving ambiguity
D. all of the above
Answer: C
120. Which type of actuator generates a good deal of power but tends to
be messy?
A. electric
B. hydraulic
o m
C. pneumatic
.c
D. both b & c
te
a
Answer: B
q M
c the world are taking steps towards
121. Research scientists all over
M patterned after the complex inter
building computers with circuits
connections existing among the human brain’s nerve cells. What name is
given to such type of computers?
A. intelligent computers
B. supercomputers
C. neural network computers
D. smart computers
Answer: C
122. Which search is equal to minimax search but eliminates the

branchesthat can’t influence the final decision?
A. depth-first search
B. breadth-first search
C. alpha-beta pruning
Answer: C

123. Which values are independant in minimax search algorithm?
A. pruned leaves x and y
B. every states are dependant
C. root is independant
Answer: A
o m
124. To which depth does the alpha-beta pruning can be applied?
.c
A. 10 states
te
a
B. 8 states
q M
C. 6 states
c
D. any depth
M
Answer: D
125. Which search is similar to minimax search?
A. hill-climbing search
B. depth-first search
C. breadth-first search
Answer: B

o m
.c
te
a
q M
c
M

76. What is the basic element for a language?
A. literal
B. variable
C. random variable

o m
.c
Answer: C
te
a
M
77. Which is the complete specification of the state of the world?
q
A. atomic event c
B. complex event
M
C. simple event
Answer: A
78. Which variable cannot be written in entire distribution as a table?
A. discrete
B. continuous
C. both a & b
Answer: B
79. Which is created by using single propositional symbol?
A. complex sentences
B. atomic sentences

C. composition sentences
Answer: B
80. Which is used to construct the complex sentences?
A. symbols
B. connectives
C. logical connectives
o m
.c
te
Answer: C
a
q M
81. How many proposition symbols are there in artificial intelligence?
c
A. 1 M
B. 2
C. 3
D. 4
Answer: B
82. How many logical connectives are there in artificial intelligence?
A. 2
B. 3
C. 4
D. 5
Answer: D
83. Which is used to compute the truth of any sentence?
A. semantics of propositional logic

B. alpha-beta pruning
C. first-order logic
D. both a & b
Answer: A
84. Which are needed to compute the logical inference algorithm?
A. logical equivalence
B. validity
o m
C. satisfiability
.c
te
a
Answer: D
q M
c
M
85. From which rule does the modus ponens are derived?
A. inference rule
B. module rule
C. both a & b
Answer: A
86. Which is also called single inference rule?
A. reference
B. resolution
C. reform
Answer: B
87. Which form is called as conjunction of disjunction of literals?

A. conjunctive normal form
B. disjunctive normal form
C. normal form
Answer: A
88. What can be viewed as single leteral of disjunction?
A. multiple clause
o m
B. combine clause
.c
te
C. unit clause
a
q M
Answer: C
c
M
89. Which is a refutation complete inference procedure for propositional
logic?
A. clauses
B. variables
C. propositional resolution
D. proposition
Answer: C
90. What kind of clauses is available in Conjunctive Normal Form?
A. disjunction of literals
B. disjunction of variables
C. conjunction of literals
D. conjunction of variables
Answer: A

91. What is the condition of literals in variables?
A. existentially quantified
B. universally quantified
C. quantified
Answer: B
o m
92. Which can be converted to inferred equivalent CNF (Conjunction
Normal Form) sentence? .c
te
A. every sentence of propositional logic a
B. every sentence of inference
q M
c
M
C. every sentence of first-order logic
Answer: C
93. Which sentence will be unsatisfiable if the CNF (Conjunction Normal

Form) sentence is unsatisfiable?
A. search statement
B. reading statement
C. replaced statement
D. original statement
Answer: D
94. Which rule is equal to resolution rule of first-order clauses?
A. propositional resolution rule
B. inference rule
C. resolution rule

Answer: A
95. At which state does the propositional literals are complementary.
A. if one variable is less
B. if one is the negation of the other
C. both a & b

o m
Answer: B
.c
te
96. What is meant by factoring? a
q M
A. removal of redundant variable
c
B. removal of redundant literal M
C. addition of redundant literal
D. addition of redundant variable
Answer: B
97. What will happen if two literals are identical?
A. remains the same
B. added as three
C. reduced to one
Answer: C
98. When the resolution is called as refutation-complete?
A. sentence is satisfiable
B. sentence is unsatisfiable

C. sentence remains the same
Answer: B
99. Computers normally solve problem by breaking them down into a

series of yes-or-no decisions represented by 1s and 0s. What is the name
of the logic that allows computers to assign numerical values that fail
somewhere between 0 and 1?
A. human logic
o m
B. fuzzy logic
.c
te
C. boolean logic
a
D. operational logic
q M
Answer: B
c
M
100. The component of an ICAI (Intelligent Computer-Asslsted Instruction)
presenting information to the student is the:
A. student model
B. problem-solving expertise
C. tutoring module
Answer: C

o m
.c
te
a
q M
c
M

51. How to increase the brightness of the pixel?
A. sound
B. amount of light
C. surface
D. waves
o m
.c
Answer: B
te
a
M
52. How many kinds of reflection are available in image perception?
q
A. 1 c
B. 2
M
C. 3
D. 4
Answer: B
53. What is meant by predicting the value of a state variable from the past?
A. specular reflection
B. diffuse reflection
C. gaussian filter
D. smoothing
Answer: D
54. How many types of image processing techniques are there in image
perception?
A. 1

B. 2
C. 3
D. 4
Answer: C
55. Which is meant by assuming any two neighboring that are both edge
pixels with consistent orientation?
A. canny edge detection
o m
B. smoothing
.c
C. segmentation
te
a
q M
Answer: A
c
M
56. What is the process of breaking an image into groups?
A. edge detection
B. smoothing
C. segmentation
Answer: C
57. How many types of 3-D image processing techniques are there in
image perception?
A. 3
B. 4
C. 5
D. 6
Answer: C

58. Which closely resembles propositional definite clause?
A. resolution
B. inference
C. conjuction
D. first-order definite clauses
Answer: D
o m
59. Which are more suitable normal form to be used with definite clause?
.c
A. positive literal
te
a
B. negative literal
q M
C. generalized modus ponens
c
D. neutral literal
M
Answer: C
60. Which will be the instance of the class datalog knowledge bases?
A. variables
B. no function symbols
C. first-order definite clauses
Answer: B
61. Which knowledge base is called as fixed point?
A. first-order definite clause are similar to propositional forward chaining
B. first-order definite clause are mismatch to propositional forward chaining
C. both a & b
Answer: A

62. Which algorithm will work backward from the goal to solve a problem?
A. forward chaining
B. backward chaining
C. hill-climb algorithm
Answer: B
63. Which is mainly used for automated reasoning? o m

.c
A. backward chaining
te
a
B. forward chaining
q M
C. logic programming
c
D. parallel programming
M
Answer: C
64. What will backward chaining algorithm will return?
A. additional statements
B. substitutes matching the query
C. logical statement
Answer: B
65. How can be the goal is thought of in backward chaining algorithm?
A. queue
B. list
C. vector
D. stack
Answer: D

66. What are used in backward chaining algorithm?
A. conjucts
B. substitution
C. composition of substitution
Answer: C
o m
67. Which algorithm are in more similar to backward chainiing algorithm?
.c
A. depth-first search algorithm
te
a
B. breadth-first search algorithm
q M
C. hill-climbing search algorithm
c
M
Answer: A
68. Which problem can frequently occur in backward chaining algorithm?
A. repeated states
B. incompleteness
C. complexity
D. both a & b
Answer: D
69. How the logic programming can be constructed?
A. variables
B. expressing knowledge in a formal language
C. graph
Answer: B

70. What form of negation does the prolog allows?
A. negation as failure
B. proposition
C. substitution
D. negation as success
Answer: A
71. Which is omitted in prolog unification algorithm? o m

.c
A. variable check
te
a
B. occur check
q M
C. proposition check
c
D. both b & c
M
Answer: B
72. How many issues are available in describing degree of belief?
A. 1
B. 2
C. 3
D. 4
Answer: B
73. What is used for probability theory sentences?
A. conditional logic
B. logic
C. extension of propositional logic
Answer: C

74. Where does the degree of belief are applied?
A. propositions
B. literals
C. variables
D. statements
Answer: A
o m
75. How many formal languages are used for stating propositions?
.c
A. 1
te
a
B. 2
q M
C. 3
c
D. 4
M
Answer: B

o m
.c
te
a
q M
c
M

26. Which modifies the performance element so that it makes better

decision?
A. performance element
B. changing element
C. learning element
o m
.c
te
Answer: C
a
q M
27. How many things are concerned in design of a learning element?
c
A. 1 M
B. 2
C. 3
D. 4
Answer: C
28. What is used in determining the nature of the learning problem?
A. environment
B. feedback
C. problem
Answer: B
A. 1

B. 2
C. 3
D. 4
Answer: C
30. Which is used for utility functions in game playing algorithm?
A. linear polynomial
B. weighted polynomial
o m
C. polynomial
.c
te
D. linear weighted polynomial
a
Answer: D
q M
c
M
31. Which is used to choose among multiple consistent hypotheses?
A. razor
B. ockham razor
C. learning element
Answer: B
32. What will happen if the hypothesis space contains the true function?
A. relizable
B. unrelizable
C. both a & b
Answer: B
33. What takes input as an object described bya set of attributes?

A. tree
B. graph
C. decision graph
D. decision tree
Answer: D
34. What will happen if the hypothesis space contains the true function?
A. realizable
o m
B. unrealizable
.c
te
C. both a & b
a
q M
Answer: B
c
M
35. What takes input as an object described by a set of attributes?
A. tree
B. graph
C. decision graph
D. decision tree
Answer: D
36. Factors which affect the performance of learner system does not
include
A. representation scheme used
B. training scenario
C. type of feedback
D. good data structures
Answer: D

A. news recommender system
B. dust cleaning machine
C. automated vehicle
Answer: A
o m
38. The process by which you become aware of messages through your
sense is called .c
te
A. organization a
B. sensation
q M
c
C. interpretation-evaluation
D. perception
M
Answer: D
39. Susan is so beautiful; I bet she is smart too. This is an example of
A. the halo effect
B. the primary effect
C. a self-fulfilling prophecy
D. the recency effect
Answer: A
40. _____ prevents you from seeing an individual as an individual rather

than as a member of a group.
A. cultural mores
B. stereotypes
C. schematas

D. attributions
Answer: C
41. When you get fired from your job and you determine it is because your
boss dislikes you, you are most likely exhibiting
A. self-promotion
B. fundamental attribution error
C. over-attribution
o m
D. self-serving bias
.c
Answer: D
te
a
42. Mindless processing is
q M
c
A. careful, critical thinking
B. inaccurate and faulty processing

M
C. information processing that relies heavily on familiar schemata
D. processing that focuses on unusual or novel events
Answer: C
43. What kind of perception is used in printing?
A. optical character recognition
B. speech recognition
C. perception
Answer: A
44. Selective retention occurs when
A. we process, store, and retrieve information that we have already selected, organized, and
interpreted

B. we make choices to experience particular stimuli
C. we make choices to avoid particular stimuli
D. we focus on specific stimuli while ignoring other stimuli
Answer: A
45. Which of the following strategies would NOT be effective at improving

your communication competence?
m
A. recognize the people, objects, and situations remain stable over time
o
c
B. recognize that each person’s frame of perception is unique
.
C. be active in perceiving
te
a
D. distinguish facts from inference
q M
Answer: A
c
M
46. _____________ is measured by the number of mental structures we
use, how abstract they are, and how elaborate they interact to shape our
perceptions.
A. intrapersonal structure
B. perceptual set
C. self-justification
D. none of the above
Answer: D
47. A perception check is
A. a cognitive bias that makes us listen only to information we already agree with.
B. a method teachers use to reward good listeners in the classroom.
C. any factor that gets in the way of good listening and decreases our ability to interpret correctly.
D. a response that allows you to state your interpretation and ask your partner whether or not that
interpretation is correct.
Answer: D

48. Which provides agents with information about the world they inhabit?
A. sense
B. perception
C. reading
D. hearing
Answer: B
o m
49. What is used to initiate the perception in the environment?
.c
A. sensor
te
a
B. read
q M
C. actuators
c
M
Answer: A
50. What is the study of light?
A. biology
B. lightology
C. photometry
Answer: C

o m
.c
te
a
q M
c
M

1. A 3-input neuron is trained to output a zero when the input is 110 and a
one when the input is 111. After generalization, the output will be zero
when and only when the input is:
A. 000 or 110 or 011 or 101
B. 010 or 100 or 110 or 101
o m
C. 000 or 010 or 110 or 100
.c
D. 100 or 111 or 101 or 001
te
a
Answer: C
q M
2. A perceptron is: c
M
A. a single layer feed-forward neural network with pre-processing
B. an auto-associative neural network
C. a double layer auto-associative neural network
D. a neural network that contains feedback
Answer: A
3. An auto-associative network is:
A. a neural network that contains no loops
B. a neural network that contains feedback
C. a neural network that has only one loop
D. a single layer feed-forward neural network with pre-processing
Answer: B

4. A 4-input neuron has weights 1, 2, 3 and 4. The transfer function islinear
with the constant of proportionality being equal to 2. The inputs are4, 10, 5
and 20 respectively. The output will be:
A. 238
B. 76
C. 119
D. 123
Answer: A
o m
.c
5. Which is true for neural networks? e
at
M
A. it has set of nodes and connections
q
c
B. each node computes it’s weighted input
M
C. node could be in excited state or non-excited state
Answer: D
6. Neuro software is:
A. a software used to analyze neurons
B. it is powerful and easy neural network
C. designed to aid experts in real world
D. it is software used by neuro surgeon
Answer: B
7. Why is the XOR problem exceptionally interesting to neural network

researchers?
A. because it can be expressed in a way that allows you to use a neural network
B. because it is complex binary operation that cannot be solved using neural networks
C. because it can be solved by a single layer perceptron

D. because it is the simplest linearly inseparable problem that exists.
Answer: D
8. What is back propagation?
A. it is another name given to the curvy function in the perceptron
B. it is the transmission of error back through the network to adjust the inputs
C. it is the transmission of error back through the network to allow weights to be adjusted so that
the network can learn.
o m
.c
Answer: C
te
a
M
9. Why are linearly separable problems of interest of neural network
q
researchers?
c
M
A. because they are the only class of problem that network can solve successfully
B. because they are the only class of problem that perceptron can solve successfully
C. because they are the only mathematical functions that are continue
D. because they are the only mathematical functions you can draw
Answer: B
10. Which of the following is not the promise of artificial neural network?
A. it can explain result
B. it can survive the failure of some nodes
C. it has inherent parallelism
D. it can handle noise
Answer: A
11. A perceptron adds up all the weighted inputs it receives, and if it

exceeds a certain value, it outputs a 1, otherwise it just outputs a 0.

A. true
B. false
C. sometimes – it can also output intermediate values as well
D. can’t say
Answer: A
12. The name for the function in question 16 is
A. step function
o m
B. heaviside function
.c
te
C. logistic function
a
D. perceptron function
q M
Answer: B
c
M
13. Having multiple perceptrons can actually solve the XOR problem
satisfactorily: this is because each perceptron can partition off a linear
part of the space itself, and they can then combine their results.
A. true – this works always, and these multiple perceptrons learn to classify even complex
problems.
B. false – perceptrons are mathematically incapable of solving linearly inseparable functions, no

matter what you do
C. true – perceptrons can do this but are unable to learn to do it – they have to be explicitly hand-
coded
D. false – just having a single perceptron is enough
Answer: C
14. The network that involves backward links from output to the input and
hidden layers is called as ____.
A. self organizing maps
B. perceptrons
C. recurrent neural network

D. multi layered perceptron
Answer: C
A. memorization
B. analogy
C. deduction
D. introduction
o m
Answer: D
.c
te
16. Following are the advantage/s of a
Decision Trees. Choose that apply.
q M
c
A. possible scenarios can be added
M
B. for data including categorical variables with different number of levels, information gain in
decision trees are biased in favor of those attributes with more levels
C. worst, best and expected values can be determined for different scenarios
D. use a white box model, if given result is provided by a model
Answer: D
A. decision trees
B. neural networks
C. propositional and fol rules
Answer: D
A. supervised learning
B. unsupervised learning

C. active learning
D. reinforcement learning
Answer: A
A. news recommendation system
B. dust cleaning machine
C. automated vehicle
o m
.c
te
Answer: A
a
q M
20. In which of the following learning the teacher returns reward and
punishment to learner? c
A. active learning
M
B. reinforcement learning
C. supervised learning
D. unsupervised learning
Answer: B
A. attributes are both numeric and nominal
B. target function takes on a discrete number of values.
C. data may have errors
Answer: D
A. data mining

B. www
C. speech recognition
Answer: D
23. Which of the following is the component of learning system?
A. goal
B. model
o m
C. learning rules
.c
te
a
Answer: D
q M
c
M
A. supervised learning
B. active learning
C. unsupervised learning
D. reinforcement learning
Answer: C
25. What will take place as the agent observes its interactions with the
world?
A. learning
B. hearing
C. perceiving
D. speech
Answer: A

o m
.c
te
a
q M
c
M

NNDL

Uploaded by

Document Information

Original Description:

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

NNDL

Uploaded by

Copyright:

Available Formats

This set of Neural Networks Multiple Choice Questions & Answers (MCQs) focuses on “Introduction″.

1. Why do we need biological neural networks?

2. What is the trend in software nowadays?

4. What is auto-association task in neural networks?

5. Does pattern classification belongs to category of non-supervised learning?

7. What is unsupervised learning?

8. Does pattern classification & grouping involve same kind of learning?

9. Does for feature mapping there’s need of supervised learning?

10. Example of a unsupervised feature map?

11. What is plasticity in neural networks?

12. What is stability plasticity dilemma ?

13. Drawbacks of template matching are?

2. The fundamental unit of network is

3. What are dendrites?

4. What is shape of dendrites like

5. Signal transmission at synapse is a?

6. How does the transmission/pulse acknowledged ?

8. Where does the chemical reactions take place in neuron?

9. Function of dendrites is?

10. What is purpose of Axon?

This set of Neural Networks online quiz focuses on “Characteristics – 2”.

1. What is approx size of neuron body(in micrometer)?

2. What is the gap at synapses(in nanometer)?

3. What is charge at protoplasm in state of inactivity?

4. What is the main constituent of neural liquid?

5. What is average potential of neural liquid in inactive state?

8. The membrane which allows neural liquid to flow will?

9. How fast is propagation of discharge signal in cells of human brain?

10. What is the function of neurotransmitter ?

1. The cell body of neuron can be analogous to what mathamatical operation?

4. What is name of above mechanism?

5. What is hebb’s rule of learning

7. What is estimate number of neurons in human cortex?

8. what is estimated density of neuron per mm^2 of cortex?

9. Why can’t we design a perfect neural network?

10. How many synaptic connection are there in human brain?

1. What is the objective of backpropagation algorithm?

3. What is true regarding backpropagation rule?

4. There is feedback in final stage of backpropagation algorithm?

5. What is true regarding backpropagation rule?

6. What is meant by generalized in statement “backpropagation is a generalized delta rule” ?

7. What are general limitations of back propagation rule?

9. Does backpropagaion learning is based on gradient descent along error surface?

10. How can learning process be stopped in backpropagation rule?

1. Probability of error in recall of stored patterns can be reduced if?

2. What is pattern environment?

3. For what purpose is pattern environment useful?

5. What consist of boltzman machine?

7. For which other task can boltzman machine be used?

9. Is exact representation of pattern environment possible?

3. How is effect false minima reduced

4. Is Boltzman law practical for implementation?

5. For practical implementation what type of approximation is used on boltzman law?

8.False minima can be reduced by deterministic updates?

9. In boltzman learning which algorithm can be used to arrive at equilibrium?

10. Boltzman learning is a?

2. Does a stochastic network will evolve differently each time it is run?

3. In case of deterministic update, what kind of equilibrium is reached?

4. In case of stochastic update, can static equilibrium be reached?

5. In case of stochastic update, what kind of equilibrium is reached?

8. Can networks with symmetric weight reach thermal equilibrium?

10. Where does a stochastic network exhibits stable states ?

This set of Neural Networks MCQs focuses on “Hopfield Model – 2”.