Unit – I
Introduction: Neural network, Human brain, biological and artificial Neurons, model of Neuron Knowledge representation, Artificial intelligence and Neural network, Network architecture, Basic Approach of the working of ANN – training, Learning and generalization.
Unit – II
Supervised learning: Single- layer networks, perception-linear separability, limitations of multi layer network architecture, back propagation algorithm (BPA) and other training algorithms, applications of adaptive multi-layer network architecture, recurrent network, feed-forword networks, radial- basis-function (RBF) networks.
Unit – III
Unsupervised learning: Winner-takes-all networks, Hamming networks, maxnet, simple competitive learning vector-quantization, counter-propagation network, adaptive resonance theory, Kohonen’s self organizing maps, principal component analysis.
Unit – IV
Associated models: Hopfield networks, brain-in-a-box network, Boltzman machine.
Unit - V
Optimization methods: Hopfield networks for-TSP, solution of simultaneous linear equations, Iterated radiant descent, simulated annealing, fenetic algorithm.
Text Books:
Simon Haykin, “Neural Networks – A Comprehensive Foundation”, Macmillan Publishing Co., New York, 1994.
K. Mahrotra, C.K. Mohan and Sanjay Ranka, “Elements of Artificial Neural Networks”, MIT Press, 1997 – Indian Reprint Penram International Publishing (India), 1997
Reference Books:
1. A Cichocki and R. Unbehauen, “Neural Networks for optimization and Signal processing”,
John Wiley and Sons, 1993.
2. J.M. Zurada, “Introduction to Artificial Neural networks”, (Indian edition) Jaico Publishers,
Mumbai, 1997.
3. Limin Fu. “Neural Networks in Computer Intelligence”, TMH.