18001025661 / 8527794500
info@sgtuniversity.org

Syllabus | B.Tech-Computer Science & Engineering | Neural Networks

  Neural Networks Learning Schedule
L T P C
Pre-requisites: CN 3 0 0 3

 COURSE DESCRIPTION

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.

COURSE OBJECTIVES

The objective of this course is to

  1. make students familiar with basic concepts and tool used in neural networks
  2. teach students structure of a neuron including biological and artificial
  3. teach learning in network (Supervised and Unsupervised)
  4. teach concepts of learning rules.

COURSE OUTCOMES

On completion of this course, the students will be able to

  1. superior for cognitive tasks and processing of  sensorial data such as vision, image- and speech recognition, control, robotics, expert systems
  2. design single and multi-layer feed-forward neural networks
  3. understand  supervised and unsupervised learning concepts & understand unsupervised learning using Kohonen networks
  4. understand training of recurrent Hopfield networks and associative memory concepts.

COURSE CONTENT

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.

TEXT BOOKS

  1. Introduction to Artificial Neural systems – Jacek M. Zurada, 1994, Jaico Publ. House

REFERENCE BOOKS

  1. Neural Networks :A Comprehensive formulation – Simon Haykin, 1998, AW
  2. Neural Networks – Kosko, 1992, PHI.
  3. Neural Network Fundamentals – N.K. Bose , P. Liang, 2002, M.H
  4. Neural Network – T.N.Shankar, University Science Press
  5. Neuro Fuzzy Systems – Lamba, V.K., University Science Press
ADMISSIONS 2021