OBJECTIVE : To study the algorithms and physical components applied in neural networks.
PRE-REQUISITE : Mathematics, Network theory.
1. INTRODUCTION [10]
Artificial Neural Network — Principles and promises — Pattern and Pattern Recognition tasks — Conventional methods — Promises of neural networks — Scope.
2. CHARACTERISTICS, NEURON MODELS [10]
Basics of ANNs - Characteristics of biological neural networks — Artificial neural networks — Terminology — Models of neuron — Topology — Activation and Syntactic Dynamics.
3. PATTI RECOGNITION METHODS AND CONCEPTS IN ANN [10]
Functional units of ANN for pattern recognition tasks — Pattern recognition by feedforward and feedbackward ANNs — Pattern Association Pattern classifier — Perception — Pattern Mapping Backpropagation learning algorithm.
4. STORAGE, CLUSTERING AND MAPPING [10]
Pattern storage (STM) — Pattern Clustering Competitive learning feature mapping — Kohonen’s Self organising networks.
5. ARCHITECTURE, MEMORY AND APPLICATIONS [10]
Neural Architecture for complex pattern recognition task — Associative memory — Data and Image compression — Pattern Classification —Spatio temporal patterns (Avalanche) — Pattern variability (Neocognitron) — Other Applications.
TEXT BOOKS :
1. J.Hertz, A.Korth and R.G.Palmer, "An Introduction to the Theory of Neural Computation", Addison Wesley, 1991.
REFERENCES :
1. Philip D. Wassermann, "Neural Computing Theory and Practice", Van Nostran Reinhold.
2. James A.Freeman and David M.Skapura, "Neural Networks; Algorithms and Applications", Addison Wesley, 1991.
3. B.Muller and J.Reinhardt, "Neural Networks: An Introduction", Addison Wesley. 1990.
4. L.B.Almedia and C.J. Wel. Lekans, "Neural Networks", Addison Wesley, 1990.
