Scribd
Upload
146 views

Jawaharlal Nehru Technological University, Hyderabad

This document outlines the course units for a Neural Networks elective course. The 8 units cover topics such as the introduction to neural networks including human brain models and network architectures; learning processes like Hebbian learning and statistical nature; single layer perceptrons including least mean square algorithm and perceptron convergence; multilayer perceptrons including backpropagation algorithm and feature detection; backpropagation details like differentiation and generalization; self organizing maps including self organizing map algorithm and learning vector quantization; neurodynamics including attractors and neurodynamical models; and Hopfield models including computer experiments. Recommended textbooks are also provided.

Uploaded by

Srinivasa Rao G
Copyright
© Attribution Non-Commercial (BY-NC)
Available Formats
Download as DOC, PDF, TXT or read online on Scribd
146 views

Jawaharlal Nehru Technological University, Hyderabad

This document outlines the course units for a Neural Networks elective course. The 8 units cover topics such as the introduction to neural networks including human brain models and network architectures; learning processes like Hebbian learning and statistical nature; single layer perceptrons including least mean square algorithm and perceptron convergence; multilayer perceptrons including backpropagation algorithm and feature detection; backpropagation details like differentiation and generalization; self organizing maps including self organizing map algorithm and learning vector quantization; neurodynamics including attractors and neurodynamical models; and Hopfield models including computer experiments. Recommended textbooks are also provided.

Uploaded by

Srinivasa Rao G
Copyright
© Attribution Non-Commercial (BY-NC)
Available Formats
Download as DOC, PDF, TXT or read online on Scribd
You are on page 1/ 2

JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY,

HYDERABAD
I Year M.Tech (CSE) II Semester

NEURAL NETWORKS
(ELECTIVE I)

UNIT I
INTRODUCTION - what is a neural network? Human Brain, Models of a Neuron,
Neural networks viewed as Directed Graphs, Network Architectures, Knowledge
Representation, Artificial Intelligence and Neural Networks

UNIT II
LEARNING PROCESS – Error Correction learning, Memory based learning, Hebbian
learing, Competitive, Boltzmann learning, Credit Asssignment Problem, Memory,
Adaption, Statistical nature of the learning process,

UNIT III
SINGLE LAYER PERCEPTRONS – Adaptive filtering problem, Unconstrained
Organization Techniques, Linear least square filters, least mean square algorithm,
learning curves, Learning rate annealing techniques, perceptron –convergence theorem,
Relation between perceptron and Bayes classifier for a Gaussian Environment

UNIT IV
MULTILAYER PERCEPTRON – Back propagation algorithm XOR problem,
Heuristics, Output representation and decision rule, Comuter experiment, feature
detection,

UNIT V
BACK PROPAGATION - back propagation and differentiation, Hessian matrix,
Generalization, Cross validation, Network pruning Techniques, Virtues and limitations of
back propagation learning, Accelerated convergence, supervised learning.

UNIT VI
SELF ORGANIZATION MAPS – Two basic feature mapping models, Self
organization map, SOM algorithm, properties of feature map, computer simulations,
learning vector quantization, Adaptive patter classification

UNIT VII
NEURO DYNAMICS – Dynamical systems, stavility of equilibrium states, attractors,
neurodynamical models , manipulation of attarctors as a recurrent network paradigm

UNIT VIII
HOPFIELD MODELS – Hopfield models, computer experiment I
TEXT BOOKS:
1. Neural networks A comprehensive foundations, Simon Hhaykin, Pearson Education 2nd
edition 2004

REFERENCE BOOKS
1. Artifical neural networks - B.Vegnanarayana Prentice Halll of India P Ltd 2005
2. Neural networks in Computer intelligence, Li Min Fu TMH 2003
3. Neural networks James A Freeman David M S kapura pearson education 2004

You might also like