Open Access Repository

Convergence in BP & Kohonen neural networks

Mirkazemi, Aram (1990) Convergence in BP & Kohonen neural networks. Unspecified thesis, University of Tasmania.

[img] PDF (Whole thesis)
whole_Mirkazemi...pdf | Request a copy
Full text restricted
Available under University of Tasmania Standard License.

Abstract

This report presents an investigation on the convergence behaviour of Backpropagation and Kohonen neural networks. The causes of convergence problems have been identified and current techniques for overcoming them are reported. Two new techniques are also presented for improvement of the convergence rate of the Backpropagation neural network. The outcome of this investigation is encapsulated in a simulation software package which includes most of the current techniques and those proposed by the author.

Item Type: Thesis (Unspecified)
Keywords: Back propagation (Artificial intelligence), Self-organizing maps, Neural networks (Computer science)
Copyright Holders: The Author
Copyright Information:

Copyright 1990 the Author - The University is continuing to endeavour to trace the copyright
owner(s) and in the meantime this item has been reproduced here in good faith. We
would be pleased to hear from the copyright owner(s).

Additional Information:

Thesis (MEngSc(Qual))--University of Tasmania, 1990. Includes bibliographical references

Date Deposited: 03 Feb 2015 03:04
Last Modified: 14 Nov 2017 03:40
Item Statistics: View statistics for this item

Actions (login required)

Item Control Page Item Control Page
TOP