Investigations in neural network learning using geometrical approach

In this thesis several methods to control the geometrical expansion process are proposed and analyzed. Our approaches turn out to gain faster training speed with satisfactory accuracy. We discuss problems both with Boolean inputs and with real-valued inputs respectively.

Saved in:

Bibliographic Details
Main Author:	Wang, Di
Other Authors:	Narendra Shivaji Chaudhari
Format:	Theses and Dissertations
Published:	2008
Subjects:	DRNTU::Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
Online Access:	https://hdl.handle.net/10356/2517
Tags:	Add Tag No Tags, Be the first to tag this record!
Institution:	Nanyang Technological University

id	sg-ntu-dr.10356-2517
record_format	dspace
spelling	sg-ntu-dr.10356-25172023-03-04T00:45:52Z Investigations in neural network learning using geometrical approach Wang, Di Narendra Shivaji Chaudhari School of Computer Engineering DRNTU::Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence In this thesis several methods to control the geometrical expansion process are proposed and analyzed. Our approaches turn out to gain faster training speed with satisfactory accuracy. We discuss problems both with Boolean inputs and with real-valued inputs respectively. DOCTOR OF PHILOSOPHY (SCE) 2008-09-17T09:04:39Z 2008-09-17T09:04:39Z 2005 2005 Thesis Wang, D. (2005). Investigations in neural network learning using geometrical approach. Doctoral thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/2517 10.32657/10356/2517 Nanyang Technological University application/pdf
institution	Nanyang Technological University
building	NTU Library
continent	Asia
country	Singapore Singapore
content_provider	NTU Library
collection	DR-NTU
topic	DRNTU::Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
spellingShingle	DRNTU::Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence Wang, Di Investigations in neural network learning using geometrical approach
description	In this thesis several methods to control the geometrical expansion process are proposed and analyzed. Our approaches turn out to gain faster training speed with satisfactory accuracy. We discuss problems both with Boolean inputs and with real-valued inputs respectively.
author2	Narendra Shivaji Chaudhari
author_facet	Narendra Shivaji Chaudhari Wang, Di
format	Theses and Dissertations
author	Wang, Di
author_sort	Wang, Di
title	Investigations in neural network learning using geometrical approach
title_short	Investigations in neural network learning using geometrical approach
title_full	Investigations in neural network learning using geometrical approach
title_fullStr	Investigations in neural network learning using geometrical approach
title_full_unstemmed	Investigations in neural network learning using geometrical approach
title_sort	investigations in neural network learning using geometrical approach
publishDate	2008
url	https://hdl.handle.net/10356/2517
_version_	1759856298946461696

Investigations in neural network learning using geometrical approach

Similar Items