ARTIFICIAL NEURAL NETWORK ,

GENETIC ALGORITHM AND FUZZY

LOGIC
AN AI BASED APPROACH

Presented By
Shruti Mehta

CONTENTS
Introduction
Artificial
Genetic
Fuzzy

Neural Network

Algorithm

Logic

WHAT IS AI?

Various definitions:
Building

intelligent entities.
Getting computers to do tasks which require human
intelligence.

But what is intelligence?

Simple things turn out to be the hardest to
automate:

Recognising

a face.
Navigating a busy street.
Understanding what someone says.

All tasks require reasoning on knowledge

WHY DO AI?
Two

main goals of AI
To understand human intelligence
better. We test theories of human
intelligence by writing programs which
emulate it.
To

create useful smart programs able

to do tasks that would normally require
a human expert.

WHO DOES AI?

Many disciplines contribute to goal of

creating/modelling intelligent entities:
Computer Science
Psychology (human reasoning)
Philosophy (nature of belief, rationality, etc)
Linguistics (structure and meaning of
language)
Human Biology (how brain works)
Subject draws on ideas from each discipline.

COMMON AI TECHNIQUES

ARTIFICIAL NEURAL NETWORK

Brief Introduction

WHAT ARE NEURAL NETWORKS?

Models of the brain and nervous system
Highly parallel

Process

information much more like the brain than a

serial computer

Learning

Very simple principles

Very complex behaviours

Applications
As

powerful problem solvers

As biological models

DEFINITION
Neural Networks(NN)are:
Mathematical models that resemble nonlinear
regression models, but are also useful to model
nonlinearly separable spaces

knowledge acquisition tools that learn from

examples

APPLICATION

pattern recognition (objects in images, voice,

medical diagnostics for diseases, etc.)

exploratory analysis (data mining)

predictive models and control

BIOLOGICAL NEURAL NETS

Pigeons as art experts (Watanabe et al. 1995)

Experiment:
Pigeon in Skinner box

Present paintings of two different artists (e.g. Chagall

/ Van Gogh)
Reward for pecking when presented a particular
artist (e.g. Van Gogh)

Pigeons were able to discriminate between Van Gogh and

Chagall with 95% accuracy (when presented with pictures
they had been trained on)
Discrimination still 85% successful for previously unseen
paintings of the artists

Pigeons do not simply memorise the pictures

They can extract and recognise patterns (the style)

They generalise from the already seen to make predictions

This is what neural networks (biological and artificial) are

good at (unlike conventional computer)

BIOLOGICAL ANALOGY
Dendrites

+
+

Synapses

+
-

Nodes

Synapses
Axon

(weights)

16

MATHEMATICAL REPRESENTATION

Advantages
Adapt

to unknown situations
Robustness: fault tolerance due to network
redundancy
Autonomous learning and generalization

Disadvantages
Not

exact
Large complexity of the network structure

For motion planning?

APPLICATION

Prediction: learning from past experience

pick

the best stocks in the market

predict weather
identify people with cancer risk

Classification
Image

processing
Predict bankruptcy for credit card companies
Risk assessment

Recognition

recognition: SNOOPE (bomb detector in U.S.

airports)
Character recognition
Handwriting: processing checks
Pattern

Data association
Not

only identify the characters that were scanned but

identify when the scanner is not working properly

Data Conceptualization
infer

grouping relationships
e.g. extract from a database the names of those
most likely to buy a particular product.

Data Filtering

e.g. take the noise out of a telephone signal, signal

smoothing

Planning

Unknown

environments
Sensor data is noisy
Fairly new approach to planning

GENETIC
ALGORITHMS

A SEARCH & OPTIMIZATION

TOOL

GENETIC ALGORITHM
Search

and Optimization Algorithm.

Based

on principles of Natural Selection

and Genetics.

Proposed

by John Holland of University of

Michigan in 1975, to study the
phenomenon of adaptation as it occurs in
nature.

PROBLEMS WITH TRADITIONAL

METHODS
Search

Space is often complicated and one

doesnt know where to look for the solution
or where to start from. Here GA comes to
help.
Traditional methods often require some
domain knowledge of the problem which
might not be readily available.
Many traditional methods are often
sensitive to initial guesses made and
provided an inappropriate guess the method
may not converge to the solution.

TERMINOLOGY
Chromosome

often encoded as a bit string,

represent a candidate solution in the
population.

Genes

are either single bits or short blocks of

adjacent bits that encode a particular
element of the candidate solution.

Alleles

are 0s or 1s in a bit string.

ELEMENTS OF A GENETIC
ALGORITHM
A

Population of chromosomes.

Fitness Function.

Genetic

Operators
- Selection
- Crossover
- Mutation

ALGORITHM (REVISITED...)
1. Start with a randomly generated population of n
chromosomes
each of size m-bits.
2. Calculate the fitness f(x) of each chromosome x in the
population.
3. Repeat the following steps:
a) Select a pair of parent chromosomes from the current
population.
b) With probability Pc, cross over the pair at a randomly
chosen point to form offspring.
c) Mutate the two offspring at each locus with probability
Pm, and place the resulting chromosomes in the new
population
4. Replace the current population with n most fit
chromosomes.
5. Go To step 2

SOME APPLICATIONS OF GA
Optimization
Automatic

Programming
Machine Learning
Economics
Immune systems
Ecology
Population genetics
Evolution and learning
Social systems
Bioinformatics
Neural Networks & Fuzzy Logic

Fuzzy Logic

WHAT IS FUZZINESS?

According to the Oxford English Dictionary..

The word fuzzy means blurred, fluffy, frayed or
indistinct.

DEFINITION

Experts rely on common sense when they solve problems.

How can we represent expert knowledge that uses
vague and ambiguous terms in a computer?
Fuzzy logic is not logic that is fuzzy, but logic that is used
to describe fuzziness. Fuzzy logic is the theory of fuzzy sets,
sets that calibrate vagueness.
Fuzzy logic is based on the idea that all things admit of
degrees. Temperature, height, speed, distance, beauty
all come on a sliding scale.
The motor is running really hot.
Tom is a very tall guy.

BIT OF HISTORY

Fuzzy, or multi-valued logic, was introduced in

the 1930s by Jan Lukasiewicz, a Polish
philosopher. While classical logic operates with
only two values 1 (true) and 0 (false),
Lukasiewicz introduced logic that extended the
range of truth values to all real numbers in the
interval between 0 and 1.
For example, the possibility that a man 181 cm
tall is really tall might be set to a value of 0.86.
It is likely that the man is tall. This work led to
an inexact reasoning technique often called
possibility theory.
34

In 1965 Lotfi Zadeh, published his famous paper

Fuzzy sets. Zadeh extended the work on
possibility theory into a formal system of
mathematical logic, and introduced a new
concept for applying natural language terms.
This new logic for representing and manipulating
fuzzy terms was called fuzzy logic

WHY FUZZY LOGIC?

Why fuzzy?
As Zadeh said, the term is concrete, immediate and
descriptive; we all know what it means. However, many
people in the West were repelled by the word fuzzy,
because it is usually used in a negative sense.

Why logic?
Fuzziness rests on fuzzy set theory, and fuzzy logic is just
a small part of that theory.

36

THE TERM FUZZY LOGIC IS USED IN

TWO SENSES:
Narrow

sense: Fuzzy logic is a branch of

fuzzy set theory, which deals (as logical
systems do) with the representation and
inference from knowledge. Fuzzy logic, unlike
other logical systems, deals with imprecise or
uncertain knowledge. In this narrow, and
perhaps correct sense, fuzzy logic is just one of
the branches of fuzzy set theory.

Broad

Sense: fuzzy logic synonymously with

fuzzy set theory

FUZZY LOGIC CAN

Represent
Enrich
Allow

vague language naturally

not replace crisp sets

flexible engineering design

Improve

model performance

Are

simple to implement

And

best of all they often work

Probability and Uncertainty

... a person suffering from hepatitis shows in

60% of all cases a strong fever, in 45% of all cases
yellowish colored skin, and in 30% of all cases
suffers from nausea ...

Stochastics and Fuzzy Logic

Complement Each Other !

INFORM 1990-1998

Slide 39

Fuzzy Set Theory

Conventional (Boolean) Set Theory:

38.7C

38C
40.1C

41.4C
Fuzzy Set Theory:

42C

39.3C

Strong Fever

37.2C

38.7C

38C
40.1C
39.3C

More-or-Less Rather Than Either-Or !

INFORM 1990-1998

41.4C

42C
Strong Fever

37.2C
Slide 40

Fuzzy Logic Example

Automotive Speed Controller
3 inputs:
speed (5 levels)
acceleration (3 levels)
distance to destination (3 levels)
1 output:
power (fuel flow to engine)
Set of rules to determine output based on
input values

Fuzzy Logic Example

1.0
Too
Slow

Slow

Optimum

Too
Fast

Fast

Speed

1.0
Decelerating

Constant

Accelerating

Acceleration

1.0
Very
Close

Close

Distant

Distance

Fuzzy Logic Example

Example Rules
IF speed is TOO SLOW and acceleration is DECELERATING,
THEN INCREASE POWER GREATLY
IF speed is SLOW and acceleration is DECREASING,
THEN INCREASE POWER SLIGHTLY
IF distance is CLOSE,
THEN DECREASE POWER SLIGHTLY
...

Fuzzy Logic Example

Output Determination
Degree of membership in an output fuzzy set now represents each
fuzzy action.
Fuzzy actions are combined to form a system output.

.7 Leave 1.0
constant

Decrease
power
greatly

Decrease
power
slightly

Leave
power
constant

Increase
power
slightly

Increase
power
greatly

.3 increase
slightly
Power

Fuzzy Logic Example

Steps
Fuzzification: determines an input's % membership in
overlapping sets.
Rules: determine outputs based on inputs and rules.
Combination/Defuzzification: combine all fuzzy
actions into a single fuzzy action and transform the
single fuzzy action into a crisp, executable system
output. May use centroid of weighted sets.

Fuzzy Logic Example

Note there would be a total of 95 different rules for all
combinations of inputs of 1, 2, or 3 at a time.
( 5x3x3 + 5x3 + 5x3 + 3x3 + 5 + 3 + 3 )
In practice, a system won't require all the rules.
System tweaked by adding or changing rules and by
adjusting set boundaries.
System performance can be very good but not usually
optimized by traditional metrics (minimize RMS error).

Fuzzy Logic Summary

Doesn't require an understanding of process but any
knowledge will help formulate rules.
Complicated systems may require several iterations to find
a set of rules resulting in a stable system.
Combining Neural Networks with fuzzy logic reduces time
to establish rules by analyzing clusters of data.
Possible applications: Master Production Schedule, Material
Requirements Planning, Inventory Capacity Planning

APPLICATION

ABS Brakes

Expert Systems

Control Units

Bullet train between Tokyo and Osaka

Video Cameras

Automatic Transmissions

THANK YOU