Scribd
Upload
3K views1 page

Neural Networks

This document outlines the modules covered in the elective course Neural Networks. The 5 modules cover: 1) principles of artificial neurons, activation functions, and single and multilayer networks 2) backpropagation training algorithms, applications, and issues 3) counterpropagation networks including Kohonen and Grossberg layers 4) statistical training methods like Boltzmann and Cauchy 5) Hopfield networks, recurrent networks, associative memory, adaptive resonance theory, and bidirectional associative memories. Recommended textbooks include Neural Computing Theory & Practice and Neural Networks.

Uploaded by

Vishnu Ajit
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as TXT, PDF, TXT or read online on Scribd
3K views1 page

Neural Networks

This document outlines the modules covered in the elective course Neural Networks. The 5 modules cover: 1) principles of artificial neurons, activation functions, and single and multilayer networks 2) backpropagation training algorithms, applications, and issues 3) counterpropagation networks including Kohonen and Grossberg layers 4) statistical training methods like Boltzmann and Cauchy 5) Hopfield networks, recurrent networks, associative memory, adaptive resonance theory, and bidirectional associative memories. Recommended textbooks include Neural Computing Theory & Practice and Neural Networks.

Uploaded by

Vishnu Ajit
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as TXT, PDF, TXT or read online on Scribd
You are on page 1/ 1

NEURAL NETWORKS (ELECTIVE - III)

RT806-3 3+1+0
Module 1
Introduction - Principles - artificial neuron - activation functions - Single la
yer & multilayer networks - Training artificial neural networks - Perception - R
epresentation - Linear separability - Learning - Training algorithms.
Module 2
Back Propagation - Training algorithm - Applications - network configurations -
Network paralysis - Local minima - temporal instability.
Module 3
Counter Propagation networks: Kebenon layer - Training the cohenen layer - Pre i
nitialising the wright vectors - statistical properties - Training the Grosbery
layer - Full counter propagation network - Application.
Module 4
Statistical methods - Boltzmann s Training - Cauche training - Artificial specific
heat methods - Applications to general non-linear optimization problems.
Module 5
Hopfield nets - Recurrent networks - stability - Associative memory - applicatio
ns - Thermo dynamic systems - Statistical Hopfield networks - Bidirectional asso
ciative memories - Continous BAM - Adaptive resonance theory - Architecture clas
sification - Implimentation.
Text Book
Neural Computing Theory & Practice - Philip D. Wasserman.
References
Neural Networks - Simon Haykins
Adaptive Pattern Recognition & Neural Networks - Pay Y.H.
An Introduction to neural computing - Chapman & Hall
Artificial Neural Networks - Robert J. Schalkoff, McGraw Hill
Artificial Neural Networks - B.Yegnanarayana, PHI

You might also like