Scribd
Upload
127 views17 pages

Soft Computing: Presentation By: C. Vinoth Kumar SSN College of Engineering

Soft computing is an approach to building intelligent systems that are tolerant of imprecision, uncertainty, and partial truth. It uses techniques like neural networks, fuzzy logic, and genetic algorithms. These systems are adaptive, can learn from experience, and are good at pattern recognition. Soft computing aims to build systems that are similar to human decision making.

Uploaded by

Lekshmi
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
127 views17 pages

Soft Computing: Presentation By: C. Vinoth Kumar SSN College of Engineering

Soft computing is an approach to building intelligent systems that are tolerant of imprecision, uncertainty, and partial truth. It uses techniques like neural networks, fuzzy logic, and genetic algorithms. These systems are adaptive, can learn from experience, and are good at pattern recognition. Soft computing aims to build systems that are similar to human decision making.

Uploaded by

Lekshmi
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 17

Soft Computing

Presentation by:
C. Vinoth Kumar
SSN College of Engineering
Soft Computing

 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”.
Soft Computing

 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


Evolution of computing
- Based on Complexity of functionality
Evolution of computing
- Based on Size
Evolution of computing
- Based on Application
SC Constituents and Conventional AI
 SC consists of several computing paradigms including:
• Neural Networks
• Fuzzy set theory
• Approximate reasoning
• Derivative-free optimization methods such as
genetic algorithms (GA) & simulated annealing (SA)
Methodologies Strengths
Neural Networks Learning and Adaptation
Knowledge Representation via
Fuzzy Set Theory
Fuzzy If - Then rules
Genetic Algorithms and
Systematic Random Search
Simulated Annealing
Conventional AI Symbolic Manipulation
Soft Computing

Fig: A Neural character recognizer and a knowledge base cooperate in


responding to 3 handwritten characters that form a word “dog”.
Conventional AI

 Artificial Intelligence is a field of study to understand


the fundamental dynamical principles underlying
biological phenomena, and refractory these dynamics
in other physical media – such as computers – making
them accessible to new kinds of experimental and
testing.
Conventional AI

 From conventional AI to computational intelligence:

i. Conventional AI manipulates symbols on the


assumption that human intelligence behavior can
be stored in symbolically structured knowledge
bases

ii. The knowledge-based system (or expert system)


is an example of the most successful conventional
AI product
Conventional AI

Fig: An expert system: one of the most successful (conventional AI products)


Conventional AI
 Several definitions have been given to conventional AI

• “AI is a programming style, where programs operate on


data according to rules in order to accomplish goals” [W.A.
Taylor]

• “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]

• “AI is the act of making computers do smart things”


[Waldrop]

 AI is changing rapidly, these definitions are already


obsolete!
Conventional AI approaches and Soft
Computing Constituents
1943 McCulloch-Pitts
1940s 1947 Cybernatics
neuron model
1956 Artificial
1950s 1957 Perceptron
Intelligence
1960 Lisp Adaline
1960s 1965 Fuzzy sets
Language Madaline
1974 Back propagation
Knowledge
Algorithm Genetic
1970s Engineering 1974 Fuzzy controller
1975 Cognitron & algorithm
(Expert Systems)
Neoconitron
1980 Self-organizing map
1982 Hopfield Net Artificial life
1985 Fuzzy modeling (TSK
1980s 1983 Boltzmann machine immune
model)
1986 Back-propagation modeling
algorithm boom
1990 Neuro-Fuzzy modeling
Genetic
1990s 1991 ANFIS
programming
1994 CANFIS
Soft Computing

 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.
Soft Computing

 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
Characteristics of Neuro Fuzzy and Soft
Computing
 With NF modeling as a backbone, SC can be
characterized as:

i. Human expertise (fuzzy if-then rules)

ii. Biologically inspired computing models (NN)

iii. New optimization techniques (GA, SA, RA)

iv. Numerical computation (no symbolic AI so far, only


numerical)

v. Fault tolerance
Characteristics of Neuro Fuzzy and Soft
Computing
vi. New application domains (adaptive signal processing,
adaptive control, nonlinear system identification,
nonlinear regression and pattern recognition)

vii. Model-free learning (ability to construct models using


only target system sample data)

viii. Intensive computation (depends highly on high-speed


number-crunching computation)

ix. Goal driven characteristics

x. Real-world applications

You might also like