Introduction to Neurofuzzy and Soft computing G Anuradha

Introduction to Neuro-fuzzy and Soft computing G. Anuradha (Lecture 1) 11/6/2020 1

What is computing? Counting, calculating The 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 11/6/2020 Hard computing Soft Computing 2

Differences between hard and soft computing Hard Computing Soft computing Precisely stated analytical model Tolerant to imprecision, uncertainty, partial truth, approximation Based on binary logic, crisp Fuzzy logic, neural nets, systems, numerical analysis, crisp probabilistic reasoning. software 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 11/6/2020 3

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 11/6/2020 4

Artificial intelligence If intelligence can be induced in machines it is called as artificial intelligence. Soft computing is a part of artificial intelligent techniques Closed related to machine intelligence/computational intelligence 11/6/2020 5

What is Soft computing Neural Networks Neuro- + Derivative- = Fuzzy Free Computing Optimization Soft Computing Fuzzy Inference systems 11/6/2020 6

Fuzzy logic Artificial Neural Networks Soft Computing Evolutionary computation 11/6/2020 Heuristics 7

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 11/6/2020 8

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 11/6/2020 9

What is the difference between Fuzzy Logic and Neural Networks? Ø Fuzzy logic allows making definite decisions based on imprecise or ambiguous data Ø ANN tries to incorporate human thinking process to solve problems without mathematically modeling them. Ø Both these methods can be used to solve nonlinear problems, and problems that are not properly specified, but they are not related. Ø ANN tries to apply the thinking process in the human brain to solve problems. 11/6/2020 10

Latest developments in the field of soft computing Areas of image processing Image retrieval Image analysis Remote sensing Data mining Swarm intelligence Diffusion process Agent’s technology 11/6/2020 11

Swarm Technology 11/6/2020 12

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 theory Approximate reasoning Derivative-free optimization methods such as genetic algorithms (GA) & simulated annealing (SA) 11/6/2020 13

SC constituents (the first three items) and conventional AI 11/6/2020 14

These methodologies form the core of SC In general, SC does not perform much symbolic manipulation SC in this sense complements conventional AI approaches 11/6/2020 15

character recognizer 11/6/2020 16

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 11/6/2020 17

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 11/6/2020 18

Expert system 11/6/2020 19

Building blocks of expert system Knowledge base: factual knowledge and heuristic knowledge Knowledge representation: in the form of rules Problem solving model: forward chaining or backward chaining Knowledge base: knowledge gained by an individual user Note: Knowledge engineering: - building an expert system Knowledge engineers: - practitioners. 11/6/2020 20

Applications of expert system 1. Diagnosis and Troubleshooting of Devices and Systems of All Kinds 2. Planning and Scheduling 3. Configuration of Manufactured Objects from Subassemblies 4. Financial Decision Making 5. Knowledge Publishing 6. Design and Manufacturing 11/6/2020 21

11/6/2020 22

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] 11/6/2020 23

“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! 11/6/2020 24

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 11/6/2020 25

These new paradigms simulate chemicobiological mechanisms responsible for natural intelligence generation SC and AI share the same long-term goal: build and understand machine intelligence An 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) 11/6/2020 26

Neural Network (NN) Imitation of the natural intelligence of the brain Parallel processing with incomplete information Nerve cells function about 106 times slower than electronic circuit gates, but human brains process visual and auditory information much faster than modern computers The brain is modeled as a continuous-time non linear dynamic system in connectionist architectures • Connectionism replaced symbolically structured representations Distributed representation in the form of weights between a massive set of interconnected neurons 11/6/2020 27

11/6/2020 28

Fuzzy set theory Human brains interpret imprecise and incomplete sensory information provided by perceptive organs Fuzzy set theory provides a systematic calculus to deal with such information linguistically It performs numerical computation by using linguistic labels stimulated by membership functions It lacks the adaptability to deal with changing external environments ==> incorporate NN learning concepts in fuzzy inference systems: NF modeling 11/6/2020 29

Evolutionary computation Natural intelligence is the product of millions of years of biological evolution Simulation of complex biological evolutionary processes GA is one computing technique that uses an evolution based on natural selection Immune modeling and artificial life are similar disciplines based on chemical and physical laws GA and SA population-based systematic random search (RA) techniques 11/6/2020 30

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) 11/6/2020 31

NF and SC Characteristics Contd… New application domains: mostly computation intensive like adaptive signal processing, adaptive control, nonlinear system identification etc Model free learning: -models are constructed based on the target system only Intensive computation: based more on computation 11/6/2020 32

NF and SC Characteristics Contd… Fault tolerance: deletion of a neuron or a rule does not destroy the system. The system performs with lesser quality Goal driven characteristics: - only the goal is important and not the path. Real world application: - large scale, uncertainties 11/6/2020 33

summary SC is evolving rapidly New techniques and applications are constantly being proposed 11/6/2020 34

11/6/2020 35