SOFT COMPUTING
Submitted to: Presented By:
Ms.Shefali Radhika Gandotra
Ms.Swati Roll no : 513/11
CONTENTS
INTRODUCTION
FEATURES OF SOFTCOMPUTING
COMPONENTS
WORKING OF THE COMPONENTS
LATEST DEVELOPMENTS
CONCLUSION
What is Soft Computing?
Soft computing is foundation of conceptual intelligence in
machines.
The idea behind soft computing is to model cognitive behaviour
of human mind.
The final aim is to develop a computer or a machine which will
work in a similar way as human beings can do.
Soft computing is an innovative approach to construct an
intelligent system.
Unique Features of Soft Computing
computationally intelligent,
possess human like expertise in
particular domain.
Can adapt to change and can learn
how to perform better .
Components of Soft Computing
Components of soft computing include:
Neural networks
Fuzzy logic
Evolutionary computing
Genetic Algorithm(GA)
NEURAL NETWORKS
Founded in 1940.
Artificial neural network mimics the
biological neuron network in function.
With the advent of high
performance computing
the subject of artificial
neural networks is at
tremendous height.
Neuron
Biological neuron
Artificial
neuron
Biological Artificial
Neuron Neuron
Cell Neuron
Dendrites Weights
Soma Net input
Axon Output
Artificial Neural Networks
Artificial neural network (ANN) is an approach that models
human brain and consists of a number of artificial neurons.
Word artificial means computer programs are able to
handle large number of computations.
Electronically modeled biological neuron.
Has many inputs and one output.
The Neuron Diagram
Bias
b
x1 w1
Activation
Induced function
Field
Output
x2 w2
v () y
Input
values
Summing
function m
u wjxj
j 1
xm wm
y (u b)
weights
Architecture Of Neural
Network
ANN ARCHITECTURES
X X
y1 z1
1 1
y1
X
y2 X
2 z2
2
X y2
y3 X
3 z3
3
Input Layer Output Input Layer Hidden Layer Output
Layer Layer
1.Single Layer Feedforward Network 2.Multilayer Feedforward Network
Xi - Input Neuron
X
z1
1
y1
X
Yi - Hidden /Output Neuron
z2
2
y2
X z3 Zi - Output Neuron
3
Input Layer Hidden Layer i = 1,2,3,4..
Learning in ANN:
Learning ruleorLearning
processis a method or a
mathematical logic which
improves theartificial neural
networks performance and
usually this rule is applied
repeatedly over the network.
Supervised learning
Unsupervised learning
Reinforcement learning
FUZZY SYSTEMS
Fuzzy set theory proposed in 1965 by Lofti A.
Zadeh is a generalization of classical set
theory.
In classical set theory, an element either
belong to or does not belong to a set and
hence, such set are termed as crisp set. But in
fuzzy set, many degrees of membership
(between o/1) are allowed.
WHAT IS FUZZY LOGIC?
Definition of fuzzy
Fuzzy not clear, blurred..
fuzzy logic is used to sort the imprecise thinking that
has brought us so much trouble.
EXAMPLE : FOR A LONG PERIOD
Dinosaurs ruled the earth for a long period.
It has not rained for a long period.
I had to wait for a doctor for a long
period.
TRADITIONAL REPRESENTATION OF LOGIC
Slow Fast
Speed = 0 Speed = 1
bool speed;
get the speed
if ( speed == 0) {
// speed is slow
}
else {
// speed is fast
}
FUZZY LOGIC REPRESENTATION
Slowest
[ 0.0 0.25 ]
Slow
Every problem must
[ 0.25 0.50 ]
be represented in
terms of fuzzy Fast
sets.
[ 0.50 0.75 ]
Fastest
[ 0.75 1.00 ]
FUZZY LOGIC REPRESENTATION
Slowest Slow Fast Fastest
float speed;
get speed
if ((speed >= 0.0)&&(speed < 0.25)) {
// speed is slowest
}
else if ((speed >= 0.25)&&(speed < 0.5))
{
// speed is slow
}
else if ((speed >= 0.5)&&(speed < 0.75))
{
// speed is fast
}
else // speed >= 0.75 && speed < 1.0
{
// speed is fastest
}
Fuzzy Logic Process
Crisp Input Fuzzification
fuzzy input
Fuzzy logic
Fuzzy Output
De-Fuzzification
Crisp Output
EVOLUTIONARY COMPUTING:
Natural Intelligence is the product of millions of years of
biological evolution.
GA is one computing technique that uses an evolution based
on natural selection.
GENETIC ALGORITHM
Search mechanism based on the Darwinian
principle of natural evolution.
Genetic Algorithms initiated and developed in the
early 1970s by John Holland are optimization
algorithms, which mimic some of the process of
natural evolution.
These criteria are required to be expressed in
terms of an object function which is usually
referred to as a fitness function.
Latest developments in the field
of soft computing
Areas of image processing
ANN aid in diagnosis of heart
infection.
Neural Networks Used To Improve
Wind Speed Forecasting
Swarm intelligence.
Summary
SC is evolving rapidly
New techniques and applications are
constantly being proposed
