05/02/2023 1

Introduction to Neuro-fuzzy and Soft computing

What is computing?

Counting, calculatingThe discipline of computing is the systematic study of algorithmic processes that describe and transform information: their theory, analysis, design, efficiency, implementation, and application. Types of computing

Hard computingSoft Computing05/02/2023 2

Differences between hard and soft computingHard Computing Soft computingPrecisely stated analytical model Tolerant to imprecision,

uncertainty, partial truth, approximation

Based on binary logic, crisp systems, numerical analysis, crisp software

Fuzzy logic, neural nets, probabilistic reasoning.

Programs are to be written Evolve their own programs

Two values logic Multi valued logic

Exact input data Ambiguous and noisy data

Strictly sequential Parallel computations

Precise answers Approximate answers

05/02/2023 3

05/02/2023 4

Essence of SC:-Accommodation with the pervasive imprecision of the real world

Principle of SC:-Exploit uncertainty to achieve robustness and better rapport with reality

Artificial intelligence

If intelligence can be induced in machines it is called as artificial intelligence. Soft computing is a part of artificial intelligent techniquesClosed related to machine intelligence/computational intelligence

05/02/2023 5

05/02/2023 6

What is Soft computing

Neural Networks

Fuzzy Inferencesystems

Neuro-Fuzzy

Computing

Derivative-Free

OptimizationSoft Computing+ =

05/02/2023 7

Artificial Neural Networks

Evolutionary computation

Fuzzy logic

Heuristics

Soft Computing

05/02/2023 8

Introduction

SC is an innovative approach to constructing computationally intelligent systems Intelligent systems that possess humanlike expertise within a specific domain, adapt themselves and learn to perform better in changing environments These systems explain how they make decisions or take actions They are composed of two features: “adaptivity” & “knowledge

05/02/2023 9

Introduction Contd….

Neural Networks (NN) that recognize patterns & adapts themselves to cope with changing environments Fuzzy inference systems that incorporate human knowledge & perform inference & decision making

Adaptivity + Expertise = NF & SC

05/02/2023 10

What is the difference between Fuzzy Logic and Neural Networks?

Fuzzy logic allows making definite decisions based on imprecise or ambiguous data

ANN tries to incorporate human thinking process to solve problems without mathematically modeling them.

Both these methods can be used to solve nonlinear problems, and problems that are not properly specified, but they are not related.

ANN tries to apply the thinking process in the human brain to solve problems.

05/02/2023 11

Latest developments in the field of soft computing

Areas of image processingImage retrieval Image analysis

Remote sensingData mining

Swarm intelligenceDiffusion processAgent’s technology

05/02/2023 12

Swarm Technology

05/02/2023 13

SC Constituents and Conventional AI

“SC is an emerging approach to computing which parallel the remarkable ability of the human mind to reason and learn in a environment of uncertainty and imprecision” [Lotfi A. Zadeh, 1992]SC consists of several computing paradigms including:

NN Fuzzy set theoryApproximate reasoningDerivative-free optimization methods such as genetic algorithms (GA) & simulated annealing (SA)

05/02/2023 14

SC constituents (the first three items) and conventional AI

05/02/2023 15

These methodologies form the core of SCIn general, SC does not perform much symbolic manipulationSC in this sense complements conventional AI approaches

05/02/2023 16

character recognizer

05/02/2023 17

Features of Conventional AI

From conventional AI to computational intelligence

Conventional AI manipulates symbols on the assumption that human intelligence behavior can be stored in symbolically structured knowledge bases: this is known as: “ The physical symbol system hypothesis The knowledge-based system (or expert system) is an example of the most successful conventional AI product

05/02/2023 18

What is an expert system?

An expert system is software that uses a knowledge base of human expertise for problem solving, or to clarify uncertainties where normally one or more human experts would need to be consulted

05/02/2023 19

Expert system

05/02/2023 20

Building blocks of expert system

Knowledge base: factual knowledge and heuristic knowledgeKnowledge representation: in the form of rulesProblem solving model: forward chaining or backward chainingKnowledge base: knowledge gained by an individual user

Note:-Knowledge engineering:- building an expert systemKnowledge engineers:- practitioners.

05/02/2023 21

Applications of expert system

1. Diagnosis and Troubleshooting of Devices and Systems of All Kinds

2. Planning and Scheduling3. Configuration of Manufactured

Objects from Subassemblies 4. Financial Decision Making5. Knowledge Publishing6. Design and Manufacturing

05/02/2023 22

05/02/2023 23

Several definitions have been given to conventional AI

“AI is the study of agents that exists in an environment and perceive and act” [S. Russel & P. Norvig] “AI is the act of making computers do smart things” [Waldrop] “AI is a programming style, where programs operate on data according to rules in order to accomplish goals” [W.A. Taylor]

05/02/2023 24

“AI is the activity of providing such machines as computers with the ability to display behavior that would be regarded as intelligent if it were observed in humans” [R. Mc Leod]“Expert system is a computer program using expert knowledge to attain high levels of performance in a narrow problem area” [D.A. Waterman]“Expert system is a caricature of the human expert, in the sense that it knows almost everything about almost nothing” [A.R. Mirzai] AI is changing rapidly, these definitions are already obsolete!

05/02/2023 25

Knowledge acquisition and representation has limited the application of AI theories (shortcoming of symbolisms) SC has become a part of “modern AI” Researchers have directed their attention toward biologically inspired methodologies such as brain modeling, evolutionary algorithm and immune modeling

05/02/2023 26

These new paradigms simulate chemico-biological mechanisms responsible for natural intelligence generationSC and AI share the same long-term goal: build and understand machine intelligenceAn intelligent system can for example sense its environment (perceive) and act on its perception (react)SC is evolving under AI influences that sprang from cybernetics (the study of information and control in human and machines)

05/02/2023 27

Neural Network (NN)

Imitation of the natural intelligence of the brainParallel processing with incomplete informationNerve cells function about 106 times slower than electronic circuit gates, but human brains process visual and auditory information much faster than modern computersThe brain is modeled as a continuous-time non linear dynamic system in connectionist architectures • Connectionism replaced symbolically structured representationsDistributed representation in the form of weights between a massive set of interconnected neurons

05/02/2023 28

05/02/2023 29

Fuzzy set theory

Human brains interpret imprecise and incomplete sensory information provided by perceptive organsFuzzy set theory provides a systematic calculus to deal with such information linguisticallyIt performs numerical computation by using linguistic labels stimulated by membership functionsIt lacks the adaptability to deal with changing external environments ==> incorporate NN learning concepts in fuzzy inference systems: NF modeling

05/02/2023 30

Evolutionary computation

Natural intelligence is the product of millions of years of biological evolutionSimulation of complex biological evolutionary processesGA is one computing technique that uses an evolution based on natural selectionImmune modeling and artificial life are similar disciplines based on chemical and physical lawsGA and SA population-based systematic random search (RA) techniques

05/02/2023 31

NF and SC characteristics

With NF modeling as a backbone, SC can be characterized as:

Human expertise (fuzzy if-then rules) Biologically inspired computing models (NN)New optimization techniques (GA, SA, RA) Numerical computation (no symbolic AI so far, only numerical)

05/02/2023 32

NF and SC Characteristics Contd…

New application domains: mostly computation intensive like adaptive signal processing, adaptive control, nonlinear system identification etcModel free learning:-models are constructed based on the target system onlyIntensive computation: based more on computation

05/02/2023 33

NF and SC Characteristics Contd…

Fault tolerance: deletion of a neuron or a rule does not destroy the system. The system performs with lesser qualityGoal driven characteristics:- only the goal is important and not the path. Real world application:- large scale, uncertainties

05/02/2023 34

summary

SC is evolving rapidlyNew techniques and applications are constantly being proposed

05/02/2023 35