COMPUTATIONAL INTELLIGENCE

Lecture # 1

Instructor: Ms. Sehrish Saba

What is Computational Intelligence?

Taxonomy proposed by Engelbrecht (2007):

2
 What is Computational Intelligence?

• is a sub-branch of AI

• is concentrated in the study of adaptive mechanisms to

enable or facilitate intelligent behavior in complex and
changing environments. (Engelbrecht, 2007).

• In the 1990’s, the term Soft Computing gained popularity.

This later on became Computational Intelligence.
 What is Computational Intelligence?

• Objective:
To mimic human intelligence

There is a lot of controversy about term Intelligence.

In 1996, IEEE Neural Networks Council defined
Artificial Intelligence as
The study of how to make computers do things
which people are currently doing better.

05/05/2022 4
 What is Computational Intelligence?

• Importance

It is a fresh area of research, internationally.

Chance of solving those unsolved problems for which

conventional techniques have failed or given poor
results (e.g. natural language processing, multiple
task in changing environment).

05/05/2022 5
 What is Computational Intelligence?

• Applications:
• Heavy Industry (Siemens, etc)
• Home Appliances (Canon,
Sony, Goldstar, Siemens).
• Automobiles (Nissan,
Mitsubishi, etc)
• Spacecrafts (NASA).
• Robotics.

05/05/2022 6
 What is Computational Intelligence?

• Applications:
• Physical Sciences and Engineering.
• Statistics
• Social Sciences.
• Behavioral Sciences.
• Biology.
• Medicine.
• Business.
• Finance.

Hundreds (if not thousands) of research papers are published every year
reporting the applicative ventures and their results.
05/05/2022 7
 Introduction
• Neural Networks
• About 100 billion neuron are there in the human
brain.

05/05/2022 8
 Introduction
• Neural Networks
• Neural networks offer a powerful method to explore,
classify and identify patterns in a data.

05/05/2022 9
 Introduction
• Evolutionary Computation
• its objective is to mimic processes from natural
evolution
• Genetic Algorithms, Genetic Programming,
Evolutionary Programming, Evolution Strategies
and so on

10
 Introduction

• Genetic Algorithms:
– Model of computation inspired from Darwin’s
evolution theory
– Based on reproduction of the solutions and
survival of the fittest

05/05/2022 11
 Introduction

• Swarm Intelligence: Particle Swarm

Algorithm
– Computational technique inspired by social
behavior of bird flocking

05/05/2022 12
 Introduction

• Swarm Intelligence: Ant Colony Algorithm

05/05/2022 13
 Introduction
• Fuzzy Logic
• Example:
– Fuzzy variable: Age
– Universe: 0 – 120 years
– Fuzzy sets: Child, Young, Old

• A fuzzy set A is characterized by a membership function μA(x)

that associates each element x with a degree of membership
value in A

• The value of membership is between 0 and 1 and it represents

the degree to which an element x belongs to the fuzzy set A

05/05/2022 14
 Introduction
• Fuzzy Systems
• Deal with imprecise entities in automated environments
– Base on fuzzy set theory and fuzzy logic.
– Most applications in control and decision making
• Over 26 000 publications of Fuzzy Logic today
• Omron’s Fuzzy Processor

05/05/2022 15
 Introduction
• Probabilistic Reasoning
– Partial belief
– Certain degree of assertion - instead of 1/0
– Logical reasoning:
• if a patient has a toothache and there is a large black hole
in the aching tooth, then the patient has a cavity
– Probabilistic reasoning:
• – if a patient has a toothache, then there is a probability of
0.9 that he has a cavity
• if a patient has a cavity, then there is a probability of 0.6
that he has a toothache

05/05/2022 16
 Introduction
• Artificial Immune Systems
– The natural immune system
has an amazing pattern
matching ability, used to
distinguish between foreign
cells entering the body
(called non-self or antigen)
and the cells belonging to
the body (called self)

05/05/2022 17
 Introduction
• Artificial Immune Systems
– Several computational models have been developed
based on the studies of natural immune system.
– Mainly used for pattern recognition problems,
classification tasks, clustering of data.
– Main application is anomaly detection (such as fraud
detection and computer virus detection)

05/05/2022 18
Applications of CI

19
20
 Marks distribution

Grading Marks
Assignments 10
Quizzes 10
Project 15
Mid Term 25
Final Term 35
Class Participation 5
TOTAL 100

05/05/2022 21
 Introduction
Course Book

Computational Intelligence: An Introduction

by Andries P. Engelbrecht,
John Wiley & Sons

Reference Books
Fundamentals of Neural Network
by Laurene Fausett
 ARTIFICIAL NEURON

Biological Neuron

• The brain may be thought of as a complex computer

• It has the following amazing characteristics:

• The ability to perform complex tasks (e.g. pattern

recognition, perception & motor control) much faster than
any computer

• The brain has the ability to solve several problems

simultaneously using distributed parts of the brain

23
 ARTIFICIAL NEURON

Biological Neuron

• The ability to learn, memorize and still generalize

• The brain is Fault Tolerant in two respects

- It is able to recognize many input signals that are

somewhat different from any signal we have seen before
(e.g. recognition of person from different pictures)

- It is able to tolerate damage to the neural system itself.

Most of the neurons are not replaced when they die. In
spite of continuous loss of neurons, we continue to learn

24
 ARTIFICIAL NEURON

Biological Neuron

• These characteristics prompted research in algorithmic

modeling of brain (biological neural systems)

• Is it possible to truly model the human brain?

Not at the present. Current successes in neural modeling

are for small artificial NNs aimed at solving a specific task

25
 ARTIFICIAL NEURON

Biological Neuron
• The basic building blocks of biological neural systems
are nerve cells, referred to as neurons
• Each consists of : SOMA, DENDRITES, AXON, and
SYNAPSE
• About 100 billion neuron in the human brain

26
 ARTIFICIAL NEURON

Biological Neuron

• The main body of the cell collects the incoming signals

from the other neurons through its dendrites

• The incoming signals are constantly being summed in the

cell body

• If the result of the summation crosses a certain threshold,

the cell body emits a signal of its own (called firing of the
neuron)

• This signal passes through the neuron’s axon, from where

the dendrites of other neurons pick it up
27
 ARTIFICIAL NEURON

Biological Neuron

• There are 1,000 to 10,000 dendrites in each neuron (few

millimeters long).

• There is only one axon (several centimeters long)

• The connection between dendrites and axon is

electrochemical and it is called synapse

• The synapses modify (enhance or inhibit) the signal while

passing it on to dendrites

28
 ARTIFICIAL NEURON

Biological Neuron

• The human learning is stored in these synapses, and the

connection of neurons with other neurons

• If stimulus at a dendrite causes the neuron to fire, then the

connection between that dendrite and axon is
strengthened

• If the arrival of stimulus does not cause the neuron to fire,

the connection weakens over time

29
ARTIFICIAL NEURON

Artificial Neuron Model

30
 ARTIFICIAL NEURON

• An artificial neuron has three components:

– Input connections (x1,x2..) with weights (w1,w2..) (the equivalent of
dendrites)
– An output (y) (the equivalent of an axon eventually linked with other
neurons’ “dendrites”.
– A computing unit (the equivalent of a living neuron’s soma). The
computing unit constantly sums the weighted inputs to produce a net
out of which the output is calculated using a non-linear activation
function (f) :
y  f ( wi xi )
 ARTIFICIAL NEURON

Artificial Neuron Model

It receives a vector X of I input signals,

X = (x1, x2, …, xI)

either from the environment or from other artificial neurons

Each input signal xi is multiplied by a weight wi to strengthen

or weaken it

The neuron computes the weighted

sum of the input signals
32
 Artificial Neural Systems
• Artificial neurons are analogous to their biological inspirers

• Here the neuron is actually a processing unit, it calculates

the weighted sum of the input signal to the neuron to
generate the activation signal a, given by

N
a   wi xi where wi is the strength of the synapse connected
i 1 to the neuron, xi is an input feature to the neuron
 Artificial Neural Systems
• The activation signal is passed through a
transformation function to produce the output of the
neuron, given by
 
y  f (a )

• The transformation function also called Activation

function can be linear, or non-linear,  
• For a linear function, the output y is proportional to
the activation signal a.
 ARTIFICIAL NEURON

Artificial Neuron Model

The weighted sum is usually called the activation of the

neuron

An activation function is applied on this weighted sum to

produce the output of the neuron

y = f(activation)

If the activation function is the unit step function, we can say

that an artificial neuron implements a nonlinear mapping
from a vector of real numbers to [-1, 1]

35