softcorecomputing-121025042248-phpapp02.pptx

softcorecomputing-121025042248-phpapp02.pptx

• 1.
  What is SoftComputing? Soft computing is an emerging approach tocomputing which parallel the remarkable ability of the human mind to reason and learn in a environment of uncertaintyand imprecision. Someof it’s principlecomponents includes: Neural Network(NN) Fuzzy Logic(FL) Genetic Algorithm(GA) These methodologies form thecoreof softcomputing.
• 2.
  GOALS OF SOFTCOMPUTING The main goal of softcomputing is todevelop intelligent machines toprovidesolutions toreal world problems, which are not modeled, or too difficult to model mathematically. It’s aim is toexploit the tolerance for Approximation, Uncertainty, Imprecision, and Partial Truth in order to achieve close resemblance with human likedecision making.
• 3.
  SOFT COMPUTING - DEVELOPMENTHISTORY Soft Computing Zadeh 1981 = Evolutionary Computing Rechenberg 1960 + Neural + Network McCulloch 1943 Fuzzy Logic Zadeh 1965 Evolutionary = Genetic + Evolution + Evolutionary + Genetic Computing Rechenberg Programming Koza Strategies Rechenberg programming Fogel Algorithms Holland 1960 1992 1965 1962 1970
• 4.
  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 Characteristicsare:- Mapping Capabilities / Pattern Association Generalisation Robustness FaultTolerance Parallel and High speed information processing
• 5.
  6 Neuron Biological neuron Model ofa neuron
• 6.
  ANN ARCHITECTURES Input LayerOutput Layer 1.Single Layer Feedforward Network Input Layer Hidden Layer Output Layer 3.Recurrent Networks Input Layer Hidden Layer Output Layer 2.MultilayerFeedforward Network Xi - Input Neuron Yi - Hidden /Output Neuron Zi - Output Neuron i = 1,2,3,4….. X1 X2 X3 y1 y2 y3 X1 X2 X3 y1 y2 z1 z2 z3 X1 X2 X3 y1 y2 z1 z2 z3
• 7.
  LEARNING METHODS OFANN NN Learning algorithms Supervised Learning Unsupervised Learning Reinforced Learning Error Correction Stochastic Hebbian Competitive Least Mean Square Backpropagation
• 8.
  FUZZY LOGIC Fuzzy settheory proposed in 1965 by A. Zadeh is a generalization of classical set theory. In classical set theory, an element either belong to or does not belong to a set and hence, such set are termed as crispset. But in fuzzyset, manydegrees of membership (between o/1) areallowed
• 9.
  FUZZY VERSES CRISP FUZZYCRISP IS R AM HONEST ? IS WATER COLORLESS ? FUZZY CRISP Extremely Honest(1) Very Honest(0.8) Honestat Times(0.4) Extremely Dishonest(0) YES!(1) NO!(0)
• 10.
  OPERTIONS CRISP 1.Union 2.Intersection 3.Complement 4.Difference FUZZY 1.Union 2.Intersection 3.Complement 4.Equality 5.Difference 6.Disjunctive Sum
• 11.
  PROPERTIES CRISP  Commutativity Associativity  Distributivity Idempotence  Identity Law Of Absorption  Transitivity  Involution  De Morgan’s Law Law Of the Excluded Middle  Law Of Contradiction FUZZY  Commutativity  Associativity  Distributivity  Idempotence  Identity  Law Of Absorption  Transitivity  Involution  De Morgan’s Law
• 12.
  GENETIC ALGORITHM Genetic Algorithmsinitiated and developed in the early 1970’s by John Holland are unorthodox search and optimization algorithms, which mimic some of the process of natural evolution. Gas perform directed random search throughagiven setof alternativewith the aim of finding the best alternative with respect tp the given criteria of goodness. These criteria are required to be expressed in termsof an object functionwhich is usuallyreferred toas a fitness function.
• 13.
  BIOLOGICAL BACKGROUND All livingorganism consist of cell. In each cell, there is a set of chromosomes which are strings of DNA and serves as a model of the organism. A chromosomes consist of genes of blocks of DNA. Each gene encodes a particular pattern. Basically, it can be said that each gene encodes a traits. Fig. Genome consisting Of chromosomes. A T G C T A G C A G T A C
• 14.
  ENCODING There are manywaysofrepresenting individual genes. Binary Encoding Octal Encoding Hexadecimal Encoding Permutation Encoding Value Encoding Tree Encoding
• 15.
  BENEFITS OF GENETICALGORITHM Easy tounderstand. Wealways getan answerand theanswergets better with time. Good for noisyenvironment. Flexible in forming building blocks for hybrid application. Has substantial historyand rangeof use. Supports multi-objectiveoptimization. Modular, separate from application.
• 16.
  APPLICATION OF SOFT COMPUTING Consumerappliancelike AC, Refrigerators, Heaters, Washing machine. Robotics like Emotional Pet robots. Food preparation appliances like Ricecookers and Microwave. Game playing like Poker, checkeretc.
• 17.
  FUTURE SCOPE Soft Computingcan beextended to include bio- informaticsaspects. Fuzzysystem can beapplied to theconstructionof moreadvanced intelligent industrial systems. Softcomputing isveryeffectivewhen it’sapplied to real world problems that are not able to solved by traditional hard computing. Softcomputing enables industrial to be innovativedue to thecharacteristics of softcomputing: tractability, lowcostand high machine intelligent quotient.
• 18.
  REFERENCES  Neural Networks,Fuzzy Logic, and Genetic Algorithms Synthesis and Application by S. Rajasekaran and G.A. Vijayalakshmi Patel  L. A. Zadeh, “Fuzzy logic, neural networks and soft computing,” in Proc. IEEE Int. Workshop Neuro Fuzzy Control, Muroran, Japan, 1993.  T. Nitta, “Application of neural networks to home appliances,” in Proc. IEEE Int. Joint Conf. Neural Networks, Nagoya, Japan, 1993.  P .J. Werbos, “Neuro-control and elastic fuzzy logic: Capabilities, conceptsand application,” IEEE Trans. Ind. Electron., Vol. 40. 1993.  Y. Doteand R.G. Hoft, Intelligent Control-PowerElectronics Systems. Oxford, U.K.: Oxford Univ. Press, 1998.  L. A. Zadeh, “Fromcomputing with numbers tocomputing with words-From manipulation of measurements to manipulation of perception,” IEEE Trans. Circuit Syst., Vol. 45, Jan 1999.
• 19.
  Any Questions