Neural Networks and Fuzzy Logic Syllabus for NIT Jalandhar
EC-454 Neural Networks and Fuzzy Logic [3 0 0 3]
Neural Networks Characteristics: History of Development in neural networks, Artificial neural net
terminology, model of a neuron, Topology, Types of learning. Supervised, Unsupervised learning.
Basic Learning laws, Hebb’s rule, Delta rule, widrow and Hoff LMS learning rule, correlation learning rule instar and ouster learning rules.
Unsupervised Learning: Competitive learning, K-means clustering algorithm, Kohonen’s feature maps. Radial Basis function neural networks- recurrent networks, Real time recurrent and learning algorithm. Introduction to Counter propagation Networks- CMAC Network, ART networks, Application of NN in pattern recognition, optimization, Control, Speech and decision making.
Fuzzy Logic: Basic concepts of Fuzzy logic, Fuzzy vs Crisp set, Linguistic variables, membership functions, operations of Fuzzy sets, Fuzzy if-then rules, Variables inference techniques, defuzzification techniques, basic Fuzzy interference algorithm, application of fuzzy logic , Fuzzy system design implementation , useful tools supporting design.
Books Recommended –
1. Berkin Riza C and Trubatch, “ Fuzzy System design principles- Building Fuzzy IF-THEN rule
bases”, IEEE Press.
2. Yegna Narayanan, “Artificial Neural Networks”. 8th Printing. PHI(2003)
3. Patterson Dan W, “Introduction to artificial Intelligence and Expert systems”, 3rd Ed., PHI
4. Simon Haykin, “Neural Networks” Pearson Education.
5. Yen and Langari, “Fuzzy Logic: Intelligence, Control and Information”, Pearson Education.
6. Jacek M Zaurada, “Introduction to artificial neural Networks Jaico Publishing Home, Fouth