720*90

Custom Search

Sem 7 - NEURAL NETWORKS

MG University S7 Electrical and Electronics (EEE) B.Tech  Syllabus



Module 1
Introduction: Principles -Artificial neuron – activation functions -Singe layer and Multilayer networks – Training artificial neural networks – Perception – Representation – Linear Separability – Learning – Training algorithms.
Module2
Back propogation: Taining Algorithim – Application – Network Configurations – Network Paralysis – Local Minima – Temporal instability.
Module 3
Counter Propogation Networks: Kebenone layer – Training the cohenen layer – Pre initialising the weight vectors – statistical properties Training the Grosbery layer – Full counter propagation network – Application.
Module 4
Statistical Methods: Boltzmann’s Training – Cauchy training – Artificial specific heat methods – applications to general non-linear optimization problems
Module 5
Hopfield nets: Recurrent networks – stability – Associative memory-applications – Thermo dynamic systems – Statistical Hopfield networks -Bidirectional associative memories – Continuous BAM – Adaptive resonance theory – Architeture classification – implimentation.
Text Book
1. Neural Computing & Practice – Philip D. Wasserman,
References
Adaptive pattern Recognition & Neural Networks – Pay Y.H.
An Introduction to neural computing – Chaoman & Hall
Artificial Neural Networks – Kishan Mehrota and Eta