EE456

ARTIFICIAL NEURAL NETWORKS

Objectives

To gain exposure in the field of neural networks and relate the human neural system into the digital world
To provide knowledge of computation and dynamical systems using neural networks

Outcomes

Acquire skill set to innovate and build a smart and intelligent engineering application using ANN

Unit – I

Perceptron Architecture- Single-Neuron Perceptron- Multi-Neuron Perceptron-

Unit – II

Perceptron Learning Rule- Constructing Learning Rules- Training Multiple-Neuron Perceptrons.

Unit – III

Simple Associative Networks- Unsupervised Hebb Rule- Hebb Rule with Decay-Instar Rule-Outstar Rule- Kohonen Rule.

Unit – IV

Adaline Network- Madaline Network -Mean Square Error- LMS Algorithm- Back Propagationa Neural networks – Hopfield Networks

Unit – V

Adaptive Filtering- Adaptive Noise Cancellation- Forecasting – Neural control applications – Character recognition.

Hagan Demuth Beale, ‘Neural network design’, PWS publishing company, 1995
Freeman, J.A and Skapura, D.M., ‘Neural networks-Algorithms, applications and programming techniques’ Addison Wesley, 1991
Satish Kumar, Neural Networks – A classroom approach’, Tata McGraw-Hill Publishing Company Limited, 2004