Scribd
Upload
8K views

Characteristics of Soft Computing

Soft computing utilizes human expertise through fuzzy logic rules and knowledge representations. It is inspired by biological systems like neural networks for tasks like pattern recognition and classification. Soft computing relies on numerical computation and optimization techniques like genetic algorithms, simulated annealing, and random search. It can learn models from data without being explicitly programmed through neural networks and adaptive fuzzy systems. Soft computing is fault tolerant and goal-driven for real-world applications where conventional approaches struggle due to uncertainties.

Uploaded by

Siva
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
8K views

Characteristics of Soft Computing

Soft computing utilizes human expertise through fuzzy logic rules and knowledge representations. It is inspired by biological systems like neural networks for tasks like pattern recognition and classification. Soft computing relies on numerical computation and optimization techniques like genetic algorithms, simulated annealing, and random search. It can learn models from data without being explicitly programmed through neural networks and adaptive fuzzy systems. Soft computing is fault tolerant and goal-driven for real-world applications where conventional approaches struggle due to uncertainties.

Uploaded by

Siva
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
You are on page 1/ 11

Characteristics of Soft Computing

Characteristics
• Human expertise • Intensive computation
• Biologically inspired • Fault tolerance
computing models • Goal driven
• New optimization characteristics
techniques • Real world application
• Numerical computation
• New application
domains
• Model-free learning
Human expertise
• Softcomputing utilized human expertise in the
form of fuzzy if then rules as well as in
conventional knowledge representations to
solve practical problems
Biologically inspired computing models
• Biological neural networks-artificial neural
networks
• Perception, pattern recognition, non linear
regression and classification problems
New optimization techniques
• Genetic algorithm
• Simulated annealing
• Random search
• Down hill simplex method
Numerical Computation
• Softcomputing mainly rely on numerical
computation
• Using symbolic techniques in soft computing
is an active research area within this field
Model free learning
• Neural networks and adaptive fuzzy system
have ability to construct models using only
target system sample data
Intensive computation
• Neuro-fuzzy and soft computing rely heavily
on high speed computation to find rules or
regularity in data sets
• It is a common feature of all areas of
computational intelligence
Fault tolerance
• Fuzzy and Neural networks exhibit this
property
• Deletion of a neuron in a neural network or a
rule in fuzzy inference system does not
destroy the system
• Performance quality deteriorates
Goal driven characteristics
• Domain specific knowledge helps to reduce
the amount of computation and search time
• Path leading from current state to the solution
does not really matter
Real world applications
• Built in uncertainities
• Conventional approaches becomes little
difficult to be solved
• Softcomputing techniques gives satisfactory
solutions to real world problems in various
disciplines all over the world

You might also like