Artificial Intelligence

1. Which of these AI domains is used by interactive voice response

(IVR) applications?
a.) Data b.) NLP c.) CV d.) None of these
2. Neural networks can be used in Character recognition.
3. The SDGs are to be achieved by which year?
a)2010 b) 2020 c)2030 d)2040
4. Which of these is medical company that uses AI to collect and
process medical and clinical data?
a) Persado b) DataRobot c) Tempus d) Clarifai
5. AI bias is also known as
a) data analysis b) machine programming
c) machine learning d) database system.
6. A ________ is a program that simulates human conversation.
a) language b) chatbot c) email d) data
7. Cogito is a popular tool in health care.
a) True b) False
8. Knowledge-based approach works best for _________ systems.
a) computer b) program c) expert d) bias
9. AI help us solve complex and interrelated global challenges.
a) True b) False
10. SDG 1 aims to end the extreme __________ globally.
a) poverty b) corruption c) deficiency d) climatic condition
11. Most of the AI modelling is done using ____________.
a) Pie chart b) Venn diagramc) Decision tree d) Bar graph
12. Massive amount of data is referred to as ________.
a) Raw data b) Big data c) Information d) Source
13. Data science is a data visualization tool.
a) True b) False
14. A problem may be broken down into cost, Quality and productivity.
15. The Object is a person or thing that receives an action.
16. Phonetics is the study of sounds we make when we speak.
17. ANN stands for
a) algorithm neural network b) artificial network neural
c) artificial neural network d) artificial neural neuron
18. The input layer gets the data which passes on to the _______ in the
hidden layer.
a) dendrite b) axon c) neuron d) nodes
19. Neural network do not have fault tolerance.
a) True b) False

20. Explain the components of NLP

There are two main components of NLP.
Natural Language Understanding (NLU): NLU involves the
following steps:
 It maps the input given in a natural language into
useful representations.
 It also analyses different aspects of the language.
Natural Language Generation (NLG): NLG is the process of producing
meaningful phrases and sentences in
21. Define tableau.
a. It is a data visualization tool widely used for business
intelligence.
b. It helps create interactive graphs and charts in the form of
dashboards and worksheets to gain business insights.
22. Define neural network and write any two applications.
An artificial neural network is a network or circuit of neurons
composed of artificial neurons or nodes.
APPLICATIONS: (Any two can be listed)
 Character recognition
 Image compression
 Stock market prediction
 Voice recognition systems
 Self – driving cars
 23. Explain the following SDGs.
a) Life below water b) Reduced inequality c) Good health and well
being
a) Life below water:
SDG 14 aims to create effective strategies to reduce
the adverse effects of increased ocean acidification and protect
marine biodiversity.
b) Reduced inequalities:
SDG 10 aims to ‘sustain the income growth of the bottom
40% of the population at a higher rate than the national average’
to reduce income inequality within and among countries.
c) Good health and well being:
SDG 3 aims to achieve universal health coverage, and reduce
common killers which are associated with child and maternal
mortality.
24. Explain any three benefits of having smart homes.
Benefits of having smart home:
 ENERGY SAVING - smart lighting and solar panels that can
even detect when occupants are in the room and adjust the
lighting as needed.
 SMART THERMOSTAT - which are wifi enabled and allow users

to set up, monitor and remotely control home temperature,

automatically modify settings according to the behaviours of
the home members and also shows energy use and thus help
track energy consumption.
 SMART SECURITY SYSTEMS – Smart locks, smart security

cameras, smart motion sensors (identify the difference

between members, visitors, pets and thieves and can raise an
alarm if suspicious behaviour is detected.)
 SMART TVs – It can connect to the Internet and play
Internet applications. Also have features such as voice or
gesture recognition.
 SMART APPLIANCES – Smart coffee maker, Smart
refrigerators (keep track of expiration dates, make
shopping lists and create recipes based on ingredients
currently at hand.)
 SENIOR MONITORING DEVICES – helps to make the home
safe and comfortable for elderly people
 SMART IRRIGATION SYSTEM - waters the lawn only when
needed and with the exact amount of water necessary.
 ROBOT ASSISTANCES - helping in household jobs or
chores, thus saving human time and energy.
 SMART PLUGS that have an energy-monitoring feature.
 A smart home routine consists of an action that sets off
other actions within your connected home. These routines
can include turning smart devices on and off or getting
latest news or weather updates.
(Any three can be explained)

25. Explain three Vs of big data.

THREE Vs OF BIG DATA:
VOLUME : It is important to have a lot of data to build an
accurate AI system
VELOCITY : The speed at which the data is received.
VARIETY : It provides the type of data collected. (Structured,
unstructured, semi-structured and mixed)
26. Write all the features of neural network.

27. Explain the types of artificial intelligence based on its functionalities

Artificial Intelligence: Type 2 (Based on Functionality):
Depending upon the functionality of AI-based applications, AI
is categorised into the types mentioned below.
Reactive machines
Reactive machines AI covers all simple and basic AI-enabled
devices. These devices do not have the capacity to store
experiences and knowledge for future actions. They process
only recent scenarios and react accordingly. Google’s Alpha Go
and IBM’s Deep Blue System are examples of reactive machines
AI devices.

Limited-memory machines
Limited-memory machines are more powerful than reactive
machines as these can store past experiences or knowledge for
a short period of time. Self-driving cars are the most common
example of limited-memory AI devices. These cars can store
the recent speed of nearby cars, the distance of other cars, the
speed limit and other information to navigate the road.
Theory of mind
Theory of mind AI is still in the development stage. It aims to
understand the human feelings and people’s reactions and can
even be able to interact socially like humans. AI researchers
are working towards the development of such AI devices.
Examples: Robots Kismet and Sophia, created in the year 2000
and 2016, respectively.

Self-awareness
Self-awareness AI will be the most powerful in the coming
future. These AI machines will have the power to beat human
intelligence and will even have human qualities such as
consciousness, sentiments and self-awareness. As of now, it is
just a vision of AI researchers and does not exist in reality.
28. Define problem scoping along with its parts and explain 4Ws of
problem scoping.
PROBLEM SCOPING:
Identifying a problem and having a focus to solve it.

MAIN PARTS OF PROBLEM SCOPING:

PROBLEM SCOPING – 4Ws PROBLEM CANVAS:

Who?
 Analysing the people getting affected directly or indirectly
by the problem.
 Finding out who the stakeholders are and details known
about them
What?
 Determines the nature of the problem.
 Gathering the evidence to prove that the problem actually
exists.
 Where?
 Focus on the context, situation and the location of the
problem.
Why?
 The above 3 canvases become the base of why we need to
solve the problem.
29. What is artificial intelligence?
A. It is the science and engineering of making intelligent
machines, especially intelligent computer programs. It is
related to the similar task of using computers to understand
human intelligence, but AI does not have to confine itself to
methods that are biologically observable.
30. Yes, but what is intelligence?
A. Intelligence is the computational part of the ability to
achieve goals in the world. Varying kinds and degrees of
intelligence occur in people, many animals and some
machines.
31. Isn't there a solid definition of intelligence that doesn't
depend on relating it to human intelligence?
A. Not yet. The problem is that we cannot yet characterize in
general what kinds of computational procedures we want to
call intelligent. We understand some of the mechanisms of
intelligence and not others.
32. Isn't AI about simulating human intelligence?
A. Sometimes but not always or even usually. On the one hand,
we can learn something about how to make machines solve
problems by observing other people or just by observing our
own methods. On the other hand, most work in AI involves
studying the problems the world presents to intelligence
rather than studying people or animals. AI researchers are
free to use methods that are not observed in people or that
involve much more computing than people can do.
 33. Q. What about other comparisons between human and
computer intelligence?
Arthur R. Jensen [Jen98], a leading researcher in human
intelligence, suggests ``as a heuristic hypothesis'' that all
normal humans have the same intellectual mechanisms and
that differences in intelligence are related to ``quantitative
biochemical and physiological conditions''. I see them as
speed, short term memory, and the ability to form accurate
and retrievable long term memories.
34. Why do we need Artificial Intelligence?
The goal of Artificial intelligence is to create intelligent machines that
can mimic human behavior. We need AI for today's world to solve
complex problems, make our lives more smoothly by automating the
routine work, saving the manpower, and to perform many more other
tasks.

35. Give some real-world applications of AI.

There are various real-world applications of AI, and some of them are
given below:
o Google Search Engine: When we start writing something on the
google search engine, we immediately get the relevant
recommendations from google, and this is because of different
AI technologies.
o Ridesharing Applications: Different ride-sharing applications
such as Uber uses AI and machine learning to determine the
type of ride, minimize the time once the car is hailed by the user,
price of the ride, etc.
o Spam Filters in Email: The AI is also used for email spam
filtering so that you can get the important and relevant emails
only in your inbox. As per the studies, Gmail successfully filters
99.9% of spam mails.
 o Social Networking: Different social networking sites such as
Facebook, Instagram, Pinterest, etc., use the AI technology for
different purposes such as face recognition and friend
suggestions, when you upload a photograph on Facebook,
understanding the contextual meaning of an emoji in Instagram,
and so on.
o Product recommendations: When we search for a product on
Amazon, we get the recommendation for similar products, and
this is because of different ML algorithms. Similarly, on Netflix,
we get personalized recommendations for movies and web
series.

36. How Artificial intelligence, Machine Learning, and Deep

Learning differ from each other?
The difference between AI, ML, and Deep Learning is given in the below table:

Artificial Machine Deep Learning

Intelligence Learning

The term The term ML The term DL was first

Artificial was first coined in the year 2000
intelligence was coined in the Igor Aizenberg.
first coined in the year 1959 by
year 1956 by Arthur
John McCarthy. Samuel.

It is a technology It is a subset It is the subset of

that is used to of AI that machine learning and AI
create intelligent learns from that is inspired by the
machines that past data and human brain cells, called
can mimic experiences. neurons, and imitates
human behavior. the working of the
human brain.
 AI completely ML deals with Deep learning deals with
deals with structured structured and
structured, semi- and semi- unstructured data.
structured data. structured
data.

It requires a huge It can work It requires a huge

amount of data to with less amount of the data
work. amount of compared to the ML.
data
compared to
deep learning
and AI.

The goal of AI is The goal of ML The goal of deep learning

to enable the is to enable is to solve the complex
machine to think the machine problems as the human
without any to learn from brain does, using various
human past algorithms.
intervention. experiences.

37. What are the types of AI?

Artificial intelligence can be divided into different types on the basis
of capabilities and functionalities.
Based on Capabilities:
o Weak AI or Narrow AI: Weak AI is capable of performing some
dedicated tasks with intelligence. Siri is an example of Weak AI.
o General AI: The intelligent machines that can perform any
intellectual task with efficiency as a human.
o Strong AI: It is the hypothetical concept that involves the
machine that will be better than humans and will surpass
human intelligence.
Based on Functionalities:
o Reactive Machines: Purely reactive machines are the basic types
of AI. These focus on the present actions and cannot store the
previous actions. Example: Deep Blue.
o Limited Memory: As its name suggests, it can store the past data
or experience for the limited duration. The self-driving car is an
example of such AI types.
o Theory of Mind: It is the advanced AI that is capable of
understanding human emotions, people, etc., in the real world.
o Self-Awareness: Self Awareness AI is the future of Artificial
Intelligence that will have their own consciousness, emotions,
similar to humans. Read More.

38. What are the different domains/Subsets of AI?

AI covers lots of domains or subsets, and some main domains are
given below:
o Machine Learning
o Deep Learning
o Neural Network
o Expert System
o Fuzzy Logic
o Natural Language Processing
o Robotics
o Speech Recognition. Read More

39. What are the types of Machine Learning?

Machine Learning can be mainly divided into three types:
a. Supervised Learning: 
b. Unsupervised Learning: 
c. Reinforcement Learning: 

40. Which programming language is used for AI?

Below are the top five programming languages that are widely used
for the development of Artificial Intelligence:
o Python
o Java
o Lisp
o R
o Prolog
Among the above five languages, Python is the most used language for
AI development due to its simplicity and availability of lots of
libraries, such as Numpy, Pandas, etc.

41. What is the intelligent agent in AI, and where are they used?
These Intelligent agents in AI are used in the following applications:
o Information Access and Navigations such as Search Engine
o Repetitive Activities
o Domain Experts
o Chatbots, etc.
42. How is machine learning related to AI?
Machine learning is a subset or subfield of Artificial intelligence. It is a
way of achieving AI. As both are the two different concepts and the
relation between both can be understood as "AI uses different
Machine learning algorithms and concepts to solve the complex
problems."
 43. What is overfitting? How can it be overcome in Machine
Learning?
When the machine learning algorithm tries to capture all the data
points, and hence, as a result, captures noise also, then overfitting
occurs in the model. Due to this overfitting issue, the algorithm shows
the low bias, but the high variance in the output. Overfitting is one of
the main issues in machine learning.
Methods to avoid Overfitting in ML:
o Cross-Validation
o Training With more data
o Regularization
o Ensembling
o Removing Unnecessary Features
o Early Stopping the training.

44. Tell one technique to avoid overfitting in neural networks?

Dropout Technique: The dropout technique is one of the popular
techniques to avoid overfitting in the neural network models. It is the
regularization technique, in which the randomly selected neurons are
dropped during training.

45. What is NLP? What are the various components of NLP?

NLP stands for Natural Language Processing, which is a branch of
artificial intelligence. It enables machines to understand, interpret,
and manipulate the human language.
Components of NLP:
There are mainly two components of Natural Language processing,
which are given below:
a. Natural Language Understanding (NLU):
It involves the below tasks:
a. To map the input to useful representations.
b. To analyze the different aspects of the language.
 b. Natural Language Generation (NLG)
a. Text Planning
b. Sentence Planning
c. Text Realization

46. What are the different components of the Expert System?

An expert system mainly contains three components:
a. User Interface: It enables a user to interact or communicate with
the expert system to find the solution for a problem.
b. Inference Engine: It is called the main processing unit or brain of
the expert system. It applies different inference rules to the
knowledge base to draw a conclusion from it. The system
extracts the information from the KB with the help of an
inference engine.
c. Knowledge Base: The knowledge base is a type of storage area
that stores the domain-specific and high-quality knowledge.

47. What is the use of computer vision in AI?

Computer vision is a field of Artificial Intelligence that is used to train
the computers so that they can interpret and obtain information from
the visual world such as images. Hence, computer vision uses AI
technology to solve complex problems such as image processing,
object detections, etc.
48. What are some misconceptions about AI?
There are lots of misconceptions about artificial intelligence since
starting its evolution. Some of these misconceptions are given below:
o AI does not require humans: The first misconception about AI is
that it does not require human. But in reality, each AI-based
system is somewhere dependent on humans and will remain.
Such as it requires human gathered data to learn about the data.
o AI is dangerous for humans: AI is not inherently dangerous for
humans, and still, it has not reached the super AI or strong AI,
 which is more intelligent than humans. Any powerful technology
cannot be harmful if it is not misused.
o AI has reached its peak stage: Still, we are so far away from the
peak stage of the AI. It will take a very long journey to reach its
peak.
o AI will take your job: It is one of the biggest confusions that AI
will take most of the jobs, but in reality, it is giving us more
opportunities for new jobs.
o AI is new technology: Although some people think that it is a
new technology, this technology actually first thought in the year
1840 through an English newspaper.

49. What is an Artificial neural network? Name some commonly

used Artificial Neural networks.
Artificial neural networks are the statistical model inspired by the
functioning of human brain cells called neurons. These neural
networks include various AI technologies such as deep learning and
machine learning.
An Artificial neural network or ANN consists of multiple layers,
including the Input layer, Output Layer, and hidden layers.
ANN, with the help of various deep learning techniques, is the AI tools
to solve various complex problems like pattern recognition, facial
recognition, and so on.
Some commonly used Artificial neural networks:
o Feedforward Neural Network
o Convolutional Neural Network
o Recurrent Neural Network
o Autoencoders

50. What is a Chatbot?

A chatbot is Artificial intelligence software or agent that can simulate
a conversation with humans or users using Natural language
processing. The conversation can be achieved through an application,
website, or messaging apps. These chatbots are also called as the
digital assistants and can interact with humans in the form of text or
through voice.
The AI chatbots are broadly used in most businesses to provide 24*7
virtual customer support to their customers, such as HDFC Eva
chatbot, Vainubot, etc.
51. What are the various techniques of knowledge representation in
AI?
Knowledge representation techniques are given below:
o Logical Representation
o Semantic Network Representation
o Frame Representation
o Production Rules

52. Which programming language is not generally used in AI, and

why?
Perl Programming language is not commonly used language for AI, as
it is the scripting language.

53. How does RL work?

The working of reinforcement learning can be understood by the
below diagram:
The RL-based system mainly consists of the following components:
o Environment: The environment is the surrounding of the agent,
where he needs to explore and act upon.
o Agent: The agent is the AI program that has sensors and
actuators and the ability to perceive the environment.
o State: It is the situation that is returned by the environment to
the agent.
o Reward: The feedback received to the agent after doing each
action.
In RL, the agent interacts with the environment in order to explore it
by doing some actions. On each action, the state of agent gets changed
or sometimes remains the same, and based on the type of action, and
he gets a reward. The reward is feedback, which may be negative or
positive based on the action.
The goal of the agent is to maximize the positive reward and to
achieve the goal of the problem.

54. What are the different areas where AI has a great impact?
Following are some areas where AI has a great impact:
o Autonomous Transportation
o Education-system powered by AI.
 o Healthcare
o Predictive Policing
o Space Exploration
o Entertainment, etc.

55. What are the different software platforms for AI development?

1. Google Cloud AI platform
2. Microsoft Azure AI platform
3. IBM Watson
4. TensorFlow
5. Infosys Nia
6. Rainbird
7. Dialogflow

56. Which algorithm is used by Facebook for face recognition?

Explain its working.
Facebook uses the DeepFace tool that uses the deep learning
algorithms for the face verification that allows the photo tag
suggestions to you when you upload a photo on Facebook. The deep
face identifies the faces in the digital images using neural network
models. The working of DeepFace is given in below steps:
o It first scans the uploaded images. It makes the 3-D model of the
image, and then rotate that image into different angles.
o After that, it starts matching. To match that image, it uses a
neural network model to determine the high-level similarities
between other photos of a person. It checks for the different
features such as the distance between the eyes, the shape of the
nose, eyes color, etc.
o Then it does the recursive checking for 68 landmark testing, as
each human face consists of 68 specific facial points.
o After mapping, it encodes the image and searches for the
information of that person.
 57. How can AI be used in fraud detection?
The artificial intelligence can be broadly helpful in fraud detection
using different machine learning algorithms, such as supervised and
unsupervised learning algorithms. The rule-based algorithms of
Machine learning helps to analyze the patterns for any transaction
and block the fraudulent transactions.
Below are the steps used in fraud detection using machine learning:
o Data extraction: The first step is data extraction. Data is
gathered through a survey or with the help of web scraping
tools. The data collection depends on the type of model, and we
want to create. It generally includes the transaction details,
personal details, shopping, etc.
o Data Cleaning: The irrelevant or redundant data is removed in
this step. The inconsistency present in the data may lead to
wrong predictions.
o Data exploration & analysis: This is one of the most crucial steps
in which we need to find out the relation between different
predictor variables.
o Building Models: Now, the final step is to build the model using
different machine learning algorithms depending on the
business requirement. Such as Regression or classification.