0% found this document useful (0 votes)
88 views10 pages

Soft Computing UNIT 1

This document introduces soft computing and its constituents which include neural networks, fuzzy logic, and genetic algorithms. Soft computing mimics human cognitive behavior and is a collection of computational techniques that help build intelligent systems. It is stochastic, allows parallel processing, and produces approximate solutions at low cost.

Uploaded by

titiki8724
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
88 views10 pages

Soft Computing UNIT 1

This document introduces soft computing and its constituents which include neural networks, fuzzy logic, and genetic algorithms. Soft computing mimics human cognitive behavior and is a collection of computational techniques that help build intelligent systems. It is stochastic, allows parallel processing, and produces approximate solutions at low cost.

Uploaded by

titiki8724
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 10

INTRODUCTION TO SOFT COMPUTING AND

NEURAL NETWORKS

UNIT 1
What is Soft Computing?
 The idea behind soft computing is to model
cognitive behavior of human mind.
 Soft computing is base of conceptual
intelligence in machines.
 Soft computing is a collection of techniques
that help us to construct computationally
intelligent system.
SOFT COMPUTING VS HARD COMPUTING
SOFT COMPUTING HARD COMPUTING
 Soft computing is stochastic in nature.  Hard computing is deterministic in
nature.
 Soft computing can perform parallel
computations.  Hard computing can perform sequential
computations.
 Takes less computation time.
 Takes more computation time.
 produces approximate answers.
 Produces exact answers.
 Low cost for solution.
 High cost for solution.
Soft Computing Constituents
Methodology Strength
Neural Network Learning and Adaption
Fuzzy Set Theory Knowledge representation
via fuzzy if-then rules
Genetic algorithm
and simulated Systematic random
annealing search
Neural network
 Neural networks mimic certain
processing capabilities of the
human brain.
 A neural network is a processing
device, either an algorithm or an
actual hardware.
 A computing world has a lot to gain
from neural networks.
Fuzzy Logic
 Fuzzy logic is a method of
processing variables that allows
the processing of several possible
truth values through a single
variable.
 Variables can have truth values
that are not only true or false, but
any real number between 0 and 1.
Genetic Algorithm
 Genetic Algorithms are used to
mimic some of the processes
observed in natural evolution.
 GA s are used to solve complex
optimization problems.
 Genetic algorithms are based on
the ideas of natural selection and
genetics.
From Conventional AI to Computational Intelligence

 Humans usually employ natural


language in reasoning and drawing
conclusions.
 Conventional AI research focuses
on trying to mimic human
intelligent behavior through the
use of language or symbolic rules.
 soft computing is developing using
AI concepts from cybernetics.
Machine Learning
TYPES OF MACHINE LEARNING
Supervised
Clustering
 Supervised Learning Learning

 Unsupervised Learning Machine Unsupervised


Association
Learning Learning
 Reinforcement Learning
Reinforcement Dimensionality
Learning Reduction
Applications using Soft Computing
 Human Expertise
 Biologically inspired computing models
 Numerical computation
 New optimization techniques
 Model free learning
 Intensive computation
 Fault tolerance

You might also like