Artificial Neural Network ,.ppt 2a6fd

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 doesn’t 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 0’s or 1’s in a bit string.

ELEMENTS OF A GENETIC ALGORITHM A

Population of chromosomes.

A

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 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 it 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 . This new logic for representing and manipulating fuzzy 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:

38.7°C

38°C 40.1°C

41.4°C Fuzzy Set Theory:

42°C

39.3°C

“Strong Fever”

37.2°C

38.7°C

38°C 40.1°C 39.3°C

“More-or-Less” Rather Than “Either-Or” ! © INFORM 1990-1998

41.4°C

42°C “Strong Fever”

37.2°C 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 hip 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 % hip 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