1 of 16

​

​

​

SOFT COMPUTING

PREPARED BY

​

S.ROHINI

ASSISTANT PROFESSOR

DEPARTMENT OF CS & IT

CPA COLLEGE

BODINAYAKANUR

Cardamom Planters’ Association College

(Re-accredited with ‘B’ Grade by NAAC)

Pankajam Nagar, Bodinayakanur – 625513

Department CS & IT

​

2 of 16

INTRODUCTION

  • A field of study that encompasses computational techniques for performing tasks that require intelligence when performed by humans

​

  • Simulation of human behavior and cognitive processes on a computer

​

  • It also known as intelligent control or Artificial intelligence

3 of 16

SOFT COMPUTING VS HARD COMPUTING

SOFT COMPUTING

HARD COMPUTING

Artificial constraints

Real time constraints

Need of robustness rather than accuracy

Need of accuracy and precision

It requires, its own program

It requires, program to be written

It follows multi-valued logic

It follows two valued logic

It requires inexact input data

It requires exact input data

It is parallel in computations

It is strictly sequential in computation

It produce approximate solution

It produce precise answers

It is non deterministic

It is deterministic

4 of 16

TECHNIQUES OF SOFTCOMPUTING

SOFT

COMPUTING

FUZZY SET

ARTIFICIAL NEURAL NETWORK

EVOLUTIONAL COMPUTING

GENETIC ALGORITHM

GENETIC PROGRAMMING

SWARM INTELLIGENCE

EXPERT SYSTEM

5 of 16

ARTIFICIAL INTELLIGENCE

  • It refers to the simulation of human intelligence in machines that are programmed to think like humans and mimic their actions.
  • The term may also be applied to any machine that exhibits traits associated with a human mind such as learning and problem-solving.

​

​

​

​

​

​

  • The ideal characteristic of artificial intelligence is its ability to rationalize and take actions that have the best chance of achieving a specific goal.

​

6 of 16

ARTIFICIAL NEURAL NETWORK

  • An artificial neural network (ANN) is the piece of a computing system designed to simulate the way the human brain analyzes and processes information.

​

  • It is the foundation of artificial intelligence (AI) and solves problems that would prove impossible or difficult by human or statistical standards.

​

​

7 of 16

CONTINUATION

  • ANNs have self-learning capabilities that enable them to produce better results as more data becomes available.

​

  • Processing units make up ANNs, which in turn consist of inputs and outputs. The inputs are what the ANN learns from to produce the desired output.

​

8 of 16

BIOLOGICAL NEURAL NETWORK VS ARTIFICIAL NEURAL NETWORK

9 of 16

FUZZY LOGIC

  • Fuzzy Logic (FL) is a method of reasoning that resembles human reasoning.
  • This approach is similar to how humans perform decision making. And it involves all intermediate possibilities between YES and NO.

​

10 of 16

11 of 16

GENETIC ALGORITHM

  • A genetic algorithm is a search heuristic that is inspired by Charles Darwin’s theory of natural evolution.
  • This algorithm reflects the process of natural selection where the fittest individuals are selected for reproduction in order to produce offspring of the next generation.
  • Five phases are considered in a genetic algorithm.
      • Initial population
      • Fitness function
      • Selection
      • Crossover
      • Mutation

​

12 of 16

13 of 16

EXPERT SYSTEM

  • EXPERT SYSTEM is an interactive and reliable computer-based decision-making system which uses both facts and heuristics to solve complex decision-making problems.

​

  • It is considered at the highest level of human intelligence and expertise.

​

  • The purpose of an expert system is to solve the most complex issues in a specific domain.

14 of 16

15 of 16

SWARM INTELLIGENCE

  • It is based on collective social behavior of organisms.

​

  • It encompasses the implementation of collective intelligence of groups of simple agents based on behavior of real world insect swarms, as a problem solving tool.

​

  • No centralized control structures.

​

  • Self organized system

16 of 16