Upload
manoj-yadav
View
637
Download
8
Tags:
Embed Size (px)
DESCRIPTION
easy and effective ....
Citation preview
Soft ComputingPresented by-
Manoj yadav
Abhishek tiwari
Harshal pandey
What is Soft Computing
Soft computing is a field of computer science which makes use of inexact solutions for problems which has no known method to compute an exact solution
It uses imprecision, uncertainty, partial truth, and approximation as input
GOALS OF SOFT OMPUTING
It’s aim is to exploit the tolerance for Approximation, Uncertainty, Imprecision, and Partial Truth in order to achieve close resemblance with human like decision making
The main goal of soft computing is to develop intelligent machines to provide solutions to real world problems, which are not modeled, or too difficult to model mathematically.
SOFT COMPUTING -DEVELOPMENT HISTORY
Soft = Evolutionary + Neural + Fuzzy
Computing Computing Network Logic
Zadeh Rechenberg McCulloch Zadeh
1981 1960 1943 1965
Evolutionary = Genetic + Evolution + Evolutionary + Genetic
Computing Programming Strategies programming Algorithms
Rechenberg Koza Rechenberg Fogel Holland
1960 1992 1965 1962 1970
Hard Computing v/s Soft Computing
Hard computingDeals with precise valuesAccurate output is neededUseful in critical systems
Soft computing Deals with assumptionsAccuracy is not necessaryUseful for routine,control, decison making tasks
Techniques in Soft Computing
• Fuzzy Systems •Neural Networks •Evolutionary Computation • Machine Learning •Probabilistic Reasoning
Neural Networks
• Founded in 1940• Artificial neural network mimics the
biological neuron network in function
k
NEURAL NETWORKS
An NN, in general, is a highly interconnected network of a large number of processing elements called neurons in an architecture inspired by the brain.
NN Characteristics are:-Mapping Capabilities / Pattern AssociationGeneralisationRobustnessFault ToleranceParallel and High speed information processing
Fuzzy Systems
• Based on fuzzy set theory and fuzzy logic• Uses numeric ranges of sets (fuzzy sets )
to measure and represent the logical evaluations of partially accurate findings
• Most applications in control and decision making
• Founded by Lofti A Zadeh
(Neuro)-fuzzy system construction
Training dataFuzzy rules(SOM, c-means etc.)
Experts
Control dataSystem
evaluation(errors)
Tuning(NN)
New system
FUZZY VERSES CRISP
FUZZYIS R AM HONEST ?
CRISP
FUZZY
ExtremelyHonest(1)
Very Honest(0.8)
Honest atTimes(0.4)
Dishonest(0Extremely
)
CRISP
YES!(1)
NO!(0)
IS WATER COLORLESS ?
OPERTIONS
CRISP FUZZY
1.Union 1.Union
2.Intersection 2.Intersection
3.Complement 3.Complement
4.Difference 4.Equality
5.Difference
6.Disjunctive Sum
Machine Learning
Pattern recognition based on training data,Classification supervised by instructor.
Unsupervised machine learning is also used where the machine learns from the given data by detecting patterns.
Orange
Apple?
Instructor
Advantages of SC
Models based on human reasoning. Closer to human thinking and biologically
inspired Models can be
Linguistic Comprehensible Fast when computing Effective in practice.
Soft Computing Applications
Heavy industry Robotic arms, Humanoid robots
Home appliances Washing machines, ACs,
Refrigerators, cameras
Automobiles Travel Speed Estimation, Sleep
Warning Systems, Driver-less cars
Spacecrafts Maneuvering of a Space
Shuttle(FL), Optimization of Fuel-efficient Solutions for space craft
SC applications: robotics
FUTURE SCOPE
Soft Computing can be extended to include bio- informatics aspects.
Fuzzy system can be applied to the construction of more advanced intelligent industrial systems.
Soft computing is very effective when it’s applied to real world problems that are not able to solved by traditional hard computing.
Soft computing enables industrial to be innovative due to the characteristics of soft computing: tractability, low cost and high machine intelligent quotient.
Any Questions