Efficient learning in neural networks

In studies of neural networks, the Multilavered Feedforward Network is the most widely used network architecture while the Backpropagation (BP)algo-rithm is the prime learning algorithm for this kind of networks. Although the BP algorithm is thought to be based on a solid theoretical background, som...

Full description

Saved in:

Bibliographic Details
Main Author:	Yin, Tong.
Other Authors:	Babri, Haroon
Format:	Theses and Dissertations
Language:	English
Published:	2009
Subjects:	DRNTU::Engineering::Electrical and electronic engineering::Computer hardware, software and systems
Online Access:	http://hdl.handle.net/10356/19615
Tags:	Add Tag No Tags, Be the first to tag this record!
Institution:	Nanyang Technological University
Language:	English

id	sg-ntu-dr.10356-19615
record_format	dspace
spelling	sg-ntu-dr.10356-196152023-07-04T15:22:50Z Efficient learning in neural networks Yin, Tong. Babri, Haroon School of Electrical and Electronic Engineering DRNTU::Engineering::Electrical and electronic engineering::Computer hardware, software and systems In studies of neural networks, the Multilavered Feedforward Network is the most widely used network architecture while the Backpropagation (BP)algo-rithm is the prime learning algorithm for this kind of networks. Although the BP algorithm is thought to be based on a solid theoretical background, some of its drawbacks hamper its use in solving problems efficiently. These draw-backs include slow convergence, the problem of local minima, and the degra-dation in performance due to practical constraints such as limited weight precision in real implementation of the algorithm. Doctor of Philosophy (EEE) 2009-12-14T06:18:11Z 2009-12-14T06:18:11Z 1998 1998 Thesis http://hdl.handle.net/10356/19615 en NANYANG TECHNOLOGICAL UNIVERSITY 214 p. application/pdf
institution	Nanyang Technological University
building	NTU Library
continent	Asia
country	Singapore Singapore
content_provider	NTU Library
collection	DR-NTU
language	English
topic	DRNTU::Engineering::Electrical and electronic engineering::Computer hardware, software and systems
spellingShingle	DRNTU::Engineering::Electrical and electronic engineering::Computer hardware, software and systems Yin, Tong. Efficient learning in neural networks
description	In studies of neural networks, the Multilavered Feedforward Network is the most widely used network architecture while the Backpropagation (BP)algo-rithm is the prime learning algorithm for this kind of networks. Although the BP algorithm is thought to be based on a solid theoretical background, some of its drawbacks hamper its use in solving problems efficiently. These draw-backs include slow convergence, the problem of local minima, and the degra-dation in performance due to practical constraints such as limited weight precision in real implementation of the algorithm.
author2	Babri, Haroon
author_facet	Babri, Haroon Yin, Tong.
format	Theses and Dissertations
author	Yin, Tong.
author_sort	Yin, Tong.
title	Efficient learning in neural networks
title_short	Efficient learning in neural networks
title_full	Efficient learning in neural networks
title_fullStr	Efficient learning in neural networks
title_full_unstemmed	Efficient learning in neural networks
title_sort	efficient learning in neural networks
publishDate	2009
url	http://hdl.handle.net/10356/19615
_version_	1772828631769284608

Efficient learning in neural networks

Similar Items