06EC753 - ARTIFICIAL NEURAL NETWORKS |
PART – A |
UNIT – I |
Introduction, history, structure and function of single neuron, neural net
architectures, neural learning, use of neural networks. |
UNIT – II |
Supervised learning, single layer networks, perceptions, linear separability,
perceptions training algorithm, guarantees of success, modifications. |
UNIT – III |
Multiclass networks-I, multilevel discrimination, preliminaries, back
propagation, setting parameter values, theoretical results. |
UNIT – IV |
Accelerating learning process, application, mandaline, adaptive multilayer
networks. |
PART – B |
UNIT – V |
Prediction networks, radial basis functions, polynomial networks,
regularization, unsupervised learning, winner take all networks. |
UNIT – VI |
Learning vector quantizing, counter propagation networks, adaptive
resonance theorem, toplogically organized networks, distance based learning,
neo-cognition. |
UNIT – VII |
Associative models, hop field networks, brain state networks, Boltzmann
machines, hetero associations. |
UNIT – VIII |
Optimization using hop filed networks, simulated annealing, random search,
evolutionary computation. |
REFERENCE |
TEXT BOOKS: |
1. Elements of Artificial Neural Networks, Kishan Mehrotra, C. K.
Mohan, Sanjay Ranka, Penram, 1997. |
Reference Books |
1. Artificial Neural Networks, R. Schalkoff, MGH, 1997.
2. Introduction to Artificial Neural Systems, J. Zurada, Jaico, 2003.
3. Neural Networks, Haykins, Pearson Edu., 1999. |
|