23
Soft Computing Ms. Mandeep Kaur Asst. Prof. (CSE) Lingaya’s University

Soft Computing-Lecture 1

Embed Size (px)

Citation preview

Page 1: Soft Computing-Lecture 1

Soft Computing

Ms. Mandeep KaurAsst. Prof. (CSE)Lingaya’s University

Page 2: Soft Computing-Lecture 1

Definition“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)

Page 3: Soft Computing-Lecture 1

What is Soft Computing?Soft Computing is the fusion of

methodologies that were designed to model and enable solutions to real world problems, which are not modeled, or too difficult to model, mathematically. These problems are typically associated with fuzzy, complex, and dynamical systems, with uncertain parameters. These systems are the ones that model the real world and are of most interest to the modern science.

Page 4: Soft Computing-Lecture 1

Contd.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”

Page 5: Soft Computing-Lecture 1

Contd.Neural Networks (NN) that

recognize patterns & adapts themselves to cope with changing environments

Fuzzy inference systems that incorporate human knowledge & perform inferencing & decision making

Adaptivity + Expertise = NF & SC

Page 6: Soft Computing-Lecture 1

Soft Computing

Fuzzy Logic

Neural Networks

Evolutionary Algorithms

Belief

Networks

SC Techniques

Page 7: Soft Computing-Lecture 1

Different methods= different rolesFuzzy Logic : the algorithms for dealing

with imprecision and uncertainty Neural Networks : the machinery for

learning and function approximation with noise

Evolutionary Algorithms : the algorithms for reinforced search and optimization

Page 8: Soft Computing-Lecture 1

Various MethodologiesThese methodologies form the core of SC In general, SC does not perform much

symbolic manipulation SC in this sense complements

conventional AI approaches

Page 9: Soft Computing-Lecture 1

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]

Artificial Intelligence (AI) is usually defined as the science of making computers do things that require intelligence when done by humans.

Page 10: Soft Computing-Lecture 1

Intelligence: “ability to learn, understand and think” (Oxford dictionary)

AI is the study of how to make computers make things which at the moment people do better.

Examples: Speech recognition, Smell, Face, Object, Intuition, Inferencing, Learning new skills, Decision making, Abstract thinking

Page 11: Soft Computing-Lecture 1

Contd.“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]

Page 12: Soft Computing-Lecture 1

Knowledge acquisition and representation has limited the application of AI theories (shortcoming of symbolicism)

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

Page 13: Soft Computing-Lecture 1

These new paradigms simulate chemico-biological 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)

Page 14: Soft Computing-Lecture 1

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”

Focuses on attempt to mimic human intelligent behavior by expressing it in language forms or symbolic rules

The knowledge-based system (or expert system) is an example of the most successful conventional AI product

Page 15: Soft Computing-Lecture 1

SC ApproachA Neural character recognizer

and a knowledge base cooperate in responding to 3 handwritten characters that form a word “dog”.

Page 16: Soft Computing-Lecture 1

Same Example

cat

cut

knowledge

Animal? cat

Neural characterrecognition

Page 17: Soft Computing-Lecture 1

AI ApproachAn expert system: one of the

most successful (conventional AI products)

Page 18: Soft Computing-Lecture 1

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

Page 19: Soft Computing-Lecture 1

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

Page 20: Soft Computing-Lecture 1

Neural networks & Fuzzy systems

low-level computational

structures that perform well when dealing with raw data,

can learn, they are opaque to the user

reasoning on a higher level, using linguistic information acquired from domain experts

lack the ability to learn and cannot adjust themselves to a new environment

Page 21: Soft Computing-Lecture 1

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 selectionImmune modeling and artificial life are

similar disciplines based on chemical and physical laws

GA and SA population-based systematic random search (RA) techniques

Page 22: Soft Computing-Lecture 1

Properties of Soft Computing methods

Page 23: Soft Computing-Lecture 1

Hybrid Connections between methods and

hybridisation possibilities. Table should be read by rows; what the technology has to offer to others.