Knowledge Based

and
Neural network Learning
 Knowledge Engineering
• Knowledge Engineering is the process of designing knowledge_x0002_based systems
(e.g. expert systems, data-driven models)
• It consist of three stages:
• Knowledge acquisition : the process of obtaining the knowledge from experts.

• Knowledge representation : selecting the most appropriate data types and

structures to represent and encode the knowledge in explicit form (e.g.lists, sets,
scripts, decision trees, object-attribute-value triplets, etc).

• Knowledge validation : testing that the knowledge-based system for

correct_x0002_ness and completeness.
 Knowledge Acquisition
Definition 1: (Knowledge Acquisition / Elicitation). The process
of gathering know-how from experts or other sources.
Definition 2: (Knowledge Acquisition / Elicitation). A transfer
from knowledge source (e.g. human experts, documents) to a
knowledge repository (e.g. expert
systems).
•Typical techniques used:
• Structured interviews
• Protocol or talk aloud analysis
• Questionnaires
• Surveys
• Observation
• Simulation
 Declarative and Procedural Knowledge
• Knowledge can be classified into:
• Declarative or descriptive knowledge — propositions or facts
describing what(e.g. which facts are known to be true).

• Procedural knowledge — logical rules describing how.

Symbolic and Sub-Symbolic Representations
• Symbolic representations convey information by discrete units
(explicit), usu_x0002_ally expressed in formal language (i.e. words,
sentences).
• Sub-symbolic representations convey information by properties
(implicit) of many objects (e.g. data, attribute values, probability
distributions, weights in neural networks, etc).

• Hybrid systems involve both types of knowledge representation

 Tacit Knowledge Capture
• Tacit Knowledge Capture
• Main approaches:
• Interviewing experts (structured interviews and stories).

• Learning by being told.

• Learning by observation.
 Knowledge Representation
Knowledge Representation Paradigms
According to McCalla and Cercone (1983):
• Semantic networks are concept graphs connected by relations, such as IS-A
relation (Dog IS-A mammal).
• First-order logic is useful for manipulation of facts (e.g. automatic
theorem_x0002_proving).
• Frames or schemata are decomposable structures or chunks used to represent
concepts.
• Production systems are algorithms represented by sets of rules
(condition_x0002_action pairs), which were used to model human reasoning.
NEURAL NETWORK LEARNING
 What is meant with learning?
• The ability of the neural network (NN) to learn form its environment
and to improve its performance through learning.

• The neural network is simulated by an environment.

• The neural network undergoes changes in its free parameters.
• The neural network responds in a new way to the environment.
 Some historical notes:
• Pavlov’s conditioning experiments:a conditioned responses,
salivation in response to auditory stimulus.
• Hebb: The organization of behavior, 1949→ long term potential , LPT,
(1973 Bliss, Lomo), AMPA receptor, Long Term Depression, LTD, NMDA
receptor.
• The nearest neighbor rule Fix and Hodges 1951.
• The idea of competitive learning : Von de Malsburg 1973, the self-
organization of orientation -sensitive nerve cells in the striate cortex.
• Lateral inhibition → Mach bands, Ernest mach 1865.
 Some historical notes:

• Statistical thermodynamics:Statistical thermodynamics in the study

of computing machinery, John Von Neumann, theory and organization
of complicated Automata, 1949.
• Reinforcement learning:Minsky 1961, Thorndike 1911.

• The problem of designing an optimum linear filter ;Kolmogorov

1942,Wiener 1949, Zadeh 1953,Gabor 1954.
 Definition of learning:

Learnng is a process by which the free parameters of a neural network

are adapted through a process of stimulation by the environment in
which the network is embedded. The type of the learning is
determined by the manner in which the parameter changes take place.
(Mendel and Mcdaren 1970)
 Five Basic Learning Rule:

1)Error-correction learning←optimum filterning

2)Memory-based learning←Memorizing the training data explicitly.

3)Hebbian Learning←Neurobiological

4)Competitive Learning←Neurobiological

5)Boltzman Learning←Statistical mechanics

 Error-correction learning
• In error correction learning
a)Error signal =desire response-output signal ek(n)= dk(n)-yk(n)
b)ek(n) actuates a control mechanism to make the output signal yk(n)
come closer to the desired response dk(n) in step by step manner.
c)A cost function ε(n)=1/2e2k(n) is the instantaneous value of the error
energy → a steady state.
d)Adelta rule or widrow -hoff rule ∆wkj(n)=ɳek(n) xj(n)
e)ɳ is the learning rate parameter.
f)The adjustment made to a synaptic weight of a neuron is proportional to
the product of the error signal and the input signal of the synapse in
question.
Wkj(n+1)=Wkj(n)+∆Wkj(n)
 Memory Based learning
• In memory based learning all of the past experiences are explicitly stored in
a large memory of correctly classified input-output examples.
=> {( xidi)}n i=1
=> Criterian used for defining the local neighbourhood of the test vector
Xtest.
=> Learning rule applied to the training examples in the local neighborhood of
xtest.
=>Nearest neighbor rule; the vector X’N ε{X1,X2,----XN}is the nearest neighbor
of Xtest if minid (xi,xtest)=d(XN,Xtest)
=>If the classified examples d(xi,di) are independently and identically
distributed according to the joint probability distribution of the example(x,d).
 Memory Based learning

=> If the sample size N is infinitely large.

=> The classification error incurred by the nearest neighbor rule is
bounded above twice the Bayes probability of error.
=>K- nearest neighbor classifier.
=> Identify the K classified patterns that lie nearest to the test vector
Xtest for some integer K.
=> Assign Xtest to the class that is most frequently represented in the K
nearest neighbors to Xtest.
 Hebbian Learning
a)If two neurons on either side of synapse(condition) are activated
simultaneously, then the strength of that synapse is selectively increased.
b)If two neurons on either side of a synapse are activated asynchronously
then that synapse is selectively weakened or eliminated.
i)Time dependent mechanism.
ii)Local mechanism( spatiotemporal cogtiguity)
iii)Interactive mechanism
iv)Conjunctional or correlational mechanism.
 Hebbian Learning:
→ A hebbian synapse increases its strength with positively correlated
presynaptic and postsynaptic signals, and decreases its strength when
signals are either uncorelated or negatively correlated.
The Hebbian learning in mathematical terms:
→∆Wkj(n)=F(yk(n),xj(n))
→ The simplest form:
∆Wkj(n)=ɳyk(n)xj(n))
→ Co-variance hypothesis :
∆Wkj=ɳ(xj-x’)(yj-y’)
 Competitive Learning:
→ The output neurons of a neural network compete among themselves to become
active.

→ A set of neurons that are all the same ( excepts for synaptic weights).

→ A limit imposed on the strength of each neuron.

→ A mechanism that permits the neurons to compete→ a winner -takes -all

→the standard competitive learning rule

∆Wkj=ɳ( xj-wkj) if neuron k wins the competition.
=0 if the neuron k loses the competition.
 Boltzmann Learning
→ The neurons constitute a recurrent structure and they operate in a
binary manner. The machine is characterized by an energy function E

→E=-½  j k Wkjxkxj, j≠k

=>Machine operates by choosing a neuron at random then flipping
the state of neuron k from the state xk to state -xk at some
temperature T with probability

→P(Xk →-Xk )=1/(1+exp(-∆Ek/T))

 Boltzmann Learning

• Clamped Conditions:
The visible neurons are al lclamped onto specific states determined by
the environment.
• Free -Running Conditions:
→ All the neurons (visible and hidden) are allowed to operate freely.
→The Boltzmann learning rule:
∆Wkj= ɳ(Pkj+ -Pkj-),
J≠K
 Credit Assignment

The credit assignment problem is the problem of assigning credit or

blame for overall outcomes to each of the internal decessions made by
the learning machine and which contributed to those outcomes.
 Temporal credit assignment problem

The temporal credit assignment problem is that it involves the instants of

time when the actions that deserve credit where actually taken.
 Structural credit assignment problem

The structural credit assignment problem in that it involves assigning

credit to the internal structures of actions generated by the system.
Learning with a teacher(Supervised Learning)

Desired
Environment Teacher Response

+
Actual Response

Learning System 

Error Signal

Fig.: Block diagram of learning with a teacher.

Learning with a teacher(Supervised Learning)

→ The teacher has knowledge of the environment

→ Error-performance surface.
 Learning without a teacher
• No labeled examples available of the function to be
learned.

a)Reinforcement learning

b)Unsupervised learning
 Reinforcement learning
Primary reinforcement
State input (vector)
Environment Critic

Heuristic Reinforcement
Action Learning System

Fig: Block Diagram of Reinforcement Learning

 Reinforcement learning

• The learning of input -output mapping is performed through continued

inteaction with the environment in order to minimize a scalar index of
performance.
• Delayed reinforcement :
→ Which means that the system observes a temporal sequence of stimuli.
→Difficult to performfor two reasons:
→There is no teacher to provide a desire response at each step of the
learning process.
→The delay incurred in the generation of the primary reinforcement signal
implies that the machine must solve a temporal credit assignment problem.
→Reinforcement learning is closely related to dynamic programming.
 Unsupervised learning

Vector describing state of environment

Environment Learning System

Fig:Block Diagram of Unsupervised learning.

 Unsupervised learning

→There is no external teacher or critic to oversee the learning

process.

→The provision is made for a task independent measure of the

quality of the representation that the network is required to learn.
The issues of learning Tasks
• Associative Memory:An associative memory is a brain like distributed
memory that learns by association.

• Auto association:A neural network is required to store a set of patterns

by repeatedly presenting then to the network .The network is
presented a partial description of an original pattern stored in it ,and
the task is to retrieve that particular pattern.

• Heteroassociation:It differs from autoassociation in that an arbitary set

of input patterns is paired with another arbitary set of output patterns.
 Heteroassociation

X Y
Pattern Associator

Input Vector Output vextor

Fig:Input output Relation of Pattern Associator

 Heteroassociation

• → Let Xk denote a key pattern and Yk denote a memorized pattern.The

pattern association is described by

→Xk →Yk K→ 1,2, ----------q.

→In an auto associative memory Xk =Yk.
→ In a heteroassociative memory Xk ≠Yk..
→ Storage phase
→ Recall phase
→q is a direct measure of the storage capacity.
THANK YOU
ANY QUESTIONS?