Course Title: Soft Computing Semester vn Course Code BTITET03B Course Type Elective it Nit L-T-P 3-0-0 Stream : Credits 3 Course Objectives: 1 To introduce a relatively new computing paradigm for creating intelligent machines useful for solving complex real world problems 2, To gain insight into the tools that make up the soft computing technique: fuzzy logic, artificial neural networks and hybrid systems, 3. To create awareness ofthe application ares of soft computing technique 44. To lear alternative solutions to the conventional problem solving techniques in image/signal processing, pattern ‘ecognition/classtfcation, control system, Course Outcomes: Aer learning the course the student will be able: 1. To use a new too! tools to solve a wide variety of real world problems. 2, To find an alternate solution, more adaptable, resilient and optimum, 3. Toapply knowledge ofthe soft computing domain to real world problems. Course Content: UNITE Artificial Neural Network:Anificial Neural Network, Biological ncuron , Arifieial neuron model , Concept of bias and threshold , McCulloch Pits Neuron Model , Implementation of logical AND, OR, XOR functions , Learning paradigms: Supervised, Unsupervised, Reinforcement , Linear neuron model , Gradient descent algorithm, Activation funetions: Binary, Bipolar (Linear, signup, log sigmoid, tan sigmoid) , Leaming mechanisms: Hebbian, Delta Rule of Pereeptron and its limitations UNITH Arlifcial Neural Network:Multlayer perceptron (MLP) and backpropagation algoritam, Application of MLP, Sel ‘organizing Peature Maps, Clustering of Learning vector quantization, Radial Basis Function networks, Hopfield network, auto associative and hetero ~ associative memory, A brief introduction to deep neural networks, convolutional neural networks, recurrent neural networks. UNITE Fuzzy Logie -I (Introduction): Basic concepts of fuzzy logic, Fuzzy sets and Crisp sets, Fuzzy set theory and ‘operations, Properties of fuzzy sets, Fuzzy and Crisp relations, Fuzzy to Crisp conversion, uNITIV Fuzzy Logie-Il (Fuzzy Membership, Rules): Membership funetions, Int Fuzzy implications and Fuzzy algorithms, Fuzzificaions&¢Defuzzification ference in fuzzy logic, Fuzzy if-then rules, Fuzzy Controller Industial applications UNITV, Evolutionary computation: Genetic Algorithms, Survival of the Fittest, Fitness Computations, Crossover, Mutation, Reproduction, Rank method, Rank space method, Simulated annealing, Evolutionary computation, Ant colony ‘optimization algorithms, Particle swarm optimization. ‘Text Books: 1. LaureneFauset, Education, 2008 Timothy Ross, “Fuzay Logic With Engineering Applications”, 3" Edition, John Wiley & Sons, 2010. JS, Jang, C1: Sun, E, Mizutani, “Neuro- Fuszy and Soft Computing”, PHI Learning Private Limited. S.N. Sivanandam, S. N. Deepa, “Principles of Soft Computing”, John Wiley & Sons, 2007, ‘undamentals of Neural Networks: Architectures, Algorithms And Applications”, PearsonReference Books: 1 John Hertz, Anders Krogh, Richard Palmer, “Introduction to the theory of neural computation”, Addison — Wesley Publishing Company, 1991. Simon Iaykin, “Neural Networks A comprehensive foundation”, Prentice Hall International Inc+1999, José C. Principe Neil R. Buliano , W. Curt Lefebvre, “Neural and Adaptive Systems: Fundamentals throwgh ‘Simulations”, John-Wiley & Sons, 2000. Peter E. Har, David G, Stork Richard 0. Duda, “Pattern Classification”, 2° Edition, 2000, SergiosTheodaridis, Konstantinos Koutroumbas, “Pattern Recognition”, 4 Edition, Academie Press, 2008, Hung T. Nguyen, Elbert A. Walker, “A First Course in Fuzzy Logic”, 3° Edition, Taylor & Francis Group, LLC, 2008. S.N. Sivanandam, §, Sumathi, S.N. Deeps, “Introduction to Fuzzy Logie using MATLAB”, Springer Verlag, 2007,