NECETRONS: NEURAL NETWORKS & APPLICATIONS

NEURAL NETWORKS & APPLICATIONS

UNIT I

INTRODUCTION: History of Neural Networks, Structure and functions of biological and artificial neuron, Neural network architectures, learning methods, evaluation of neural networks.

UNIT II

SUPERVISED LEARNING - I: McCulloch- Pitts neuron model, perception learning, Delta learning, Windrow- Hoff learning rules, linear seperability, Adeline modification.

UNIT III

SUPERVISED LEARNING –II MULTI LAYER NETWORKS: Architectures, Madalines, Back propagation algorithm, importance of learning parameter and momentum term, radial basis functions, polynomial networks.

UNIT IV&V

UNSUPERVISED LEARNING : Winner-Take- all learning, out star learning, learning vector quantizers, Counter propagation networks, Kohonen self – organizing networks, Grossberg layer, adaptive resonance theory, Hamming net.

UNIT VI

ASSOCIATIVE MEMORIES: Hebbian learning rule, continues and discrete Hopfild networks, recurrent and associative memory, Boltzman machines, Bi-directional associative memory.

UNIT VII&VIII

APPLICATIONS OF NEURAL NETWORKS: Optimization, Travelling Salesman problem, solving simultaneous linear equations, application in pattern recognition and image processing. Pattern recognition, Optimization, Associative memories, speech and decision-making. VLSI implementation of neural networks.