EI 8401 Fuzzy Logic & Neural Networks EI 8th (Eight) sem Electronics and Instrumentation(EI) Syllabus
Fuzzy system introduction, Fuzzy relation, Membership function, Fuzzy matrices and entropy, Fuzzy
operation and composition.
Fuzzy Variables, Linguistic variables, measures of fuzziness, concepts of defuzzification, Fuzzy control applications.
Fundamentals of Artificial Neural networks- Biological prototype – Artificial neuron, Activation functions, Single layer and multiplayer networks. Training Artificial neural networks, Preceptrons, Exclusive Or Problem – Linear seperability, Storage efficiency, Preceptron learning, perceptron training algorithms. Back propagation, Training algorithm, network configurations, Network paralysis, Local minima, temporal instability.
Counter propagation networks, Kohonen layer, Training the kohonen layer, Pre processing the inputted
vectors, Initialising the wright vectors, Statistical properties, Training the grosberg layer. Full counter propagation networks, Applications. Statistical methods, Boltzman training, Cauchy training, Artificial specific heat methods, Applications to general non-linear optimization problems. Back propagation and cauchy training.
Hopfield nets, Recurrent networks, Stability, Associative memory, Thermodynamic systems, Statistical Hopfiled networks, Applications. Bi-directional associative memories, Retrieving on stored association, Encoding the associations.
Laurence Fausett, “Fundamentals of Neural Networks”, Prentice Hall.
Zmmermann H.J., “Fuzzy Set Theory and its Applications”, Allied Publishers Ltd.
Klir G.J., and Folger T., “Fuzzy Sets, Uncertainty and Information”, Prentice Hall.
Limin Fu., “Neural Networks in Computer Intelligence”, McGraw Hill.
Zuroda J.M., “Introduction to Artificial Neural Systems”, Jaico Publishing.
Haykin S., "Artificial Neural Network: A Comprehensive Foundation: Asia Pearson Pub.