|Neural Networks||Learning Schedule|
This course will cover basic neural network architectures and learning algorithms, for applications in pattern recognition, image processing, and computer vision. Three forms of learning will be introduced (i.e., supervised, unsupervised and reinforcement learning) and applications of these will be discussed. The students will have a chance to try out several of these models on practical problems.
The objective of this course is to
- make students familiar with basic concepts and tool used in neural networks
- teach students structure of a neuron including biological and artificial
- teach learning in network (Supervised and Unsupervised)
- teach concepts of learning rules.
On completion of this course, the students will be able to
- superior for cognitive tasks and processing of sensorial data such as vision, image- and speech recognition, control, robotics, expert systems
- design single and multi-layer feed-forward neural networks
- understand supervised and unsupervised learning concepts & understand unsupervised learning using Kohonen networks
- understand training of recurrent Hopfield networks and associative memory concepts.
Unit I: Introduction
Structure of biological neurons relevant to ANNs., Models of ANNs; Feedforward & feedback networks; learning rules; Hebbian learning rule, perception learning rule, delta learning rule, Widrow-Hoff learning rule, correction learning rule, Winner –lake all learning rule, etc.
Unit II: Single layer Perception Classifier and Multi-layer Feed forward Networks
Classification model, Features & Decision regions; training & classification using discrete perceptron, algorithm, single layer continuous perceptron networks for linearly separable classifications, linearly non-separable pattern classification, Delta learning rule for multi-perceptron layer, Generalized delta learning rule, Error back-propagation training, learning factors, Examples.
Unit III: Single layer feedback Networks
Basic Concepts, Hopfield networks, Training & Examples. Associative memories: Linear Association, Basic Concepts of recurrent.
Unit IV: Auto associative memory
Retrieval algorithm, storage algorithm; By directional associative memory, Architecture, Association encoding & decoding, Stability.
Unit V: Self organizing networks
UN supervised learning of clusters, winner-take-all learning, recall mode, Initialization of weights, seperability limitations.
- Introduction to Artificial Neural systems – Jacek M. Zurada, 1994, Jaico Publ. House
- Neural Networks :A Comprehensive formulation – Simon Haykin, 1998, AW
- Neural Networks – Kosko, 1992, PHI.
- Neural Network Fundamentals – N.K. Bose , P. Liang, 2002, M.H
- Neural Network – T.N.Shankar, University Science Press
- Neuro Fuzzy Systems – Lamba, V.K., University Science Press