Prerequisites: CA 722
Outline:
1. Introduction - Artificial Neural Network – Principles and promises – Pattern and Pattern Recognition tasks – Conventional methods – Promises of neural networks – Scope - Characteristics, Neuron models.
2. Basics of ANNs - Characteristics of biological neural networks – Artificial neural networks – Terminology – Models of neuron – Topology – Activation and Syntactic Dynamics.
3. Pattern Recognition Methods And Concepts In ANN - Functional units of ANN for pattern recognition tasks – Pattern recognition by feed forward and feed back ANNs – Pattern Association – Pattern classifier – Perception – Pattern Mapping – Back propagation learning algorithm.
4. Storage, Clustering and mapping - Pattern storage(STM) – Pattern Clustering – Competitive Learning – feature mapping – Kohonen’s Self organising networks - Architecture, memory and applications - Neural Architecture for complex pattern recognition task – Associative memory.
5. Data and Image compression – Pattern Classification – Spatio temporal patterns(Avalanche) – Pattern variability(Neocognitron) – Other Applications.
Books:
1. J.Hertz, A.Korth and R.G.Palmer, "An Introduction to the Theory of Neural Computation", Addison Wesley, 1991.
2. James A.Freeman and David M.Skapura, "Neural Networks: Algorithms and Applications", Addison Wesley, 1991.
