On extracting knowledge from neural networks

The primary contribution of the thesis is an algorithm that overcomes the significant limitations of previous methods by taking an approach to the task of extracting comprehensible rules from trained networks. This algorithm is called HyperNeuro. Given a neural network, HyperNeuro extracts linear if...

Full description

Saved in:

Bibliographic Details
Main Author:	Tan, Kian Huat.
Other Authors:	Chen, Yan Qiu
Format:	Theses and Dissertations
Published:	2008
Subjects:	DRNTU::Engineering::Electrical and electronic engineering::Computer hardware, software and systems
Online Access:	http://hdl.handle.net/10356/3372
Tags:	Add Tag No Tags, Be the first to tag this record!
Institution:	Nanyang Technological University

id	sg-ntu-dr.10356-3372
record_format	dspace
spelling	sg-ntu-dr.10356-33722023-07-04T15:13:24Z On extracting knowledge from neural networks Tan, Kian Huat. Chen, Yan Qiu School of Electrical and Electronic Engineering Chen, Lihui DRNTU::Engineering::Electrical and electronic engineering::Computer hardware, software and systems The primary contribution of the thesis is an algorithm that overcomes the significant limitations of previous methods by taking an approach to the task of extracting comprehensible rules from trained networks. This algorithm is called HyperNeuro. Given a neural network, HyperNeuro extracts linear if-then-else decision rules from trained neural networks that have been trained for classification problems.. Master of Engineering 2008-09-17T09:28:45Z 2008-09-17T09:28:45Z 2002 2002 Thesis http://hdl.handle.net/10356/3372 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::Electrical and electronic engineering::Computer hardware, software and systems
spellingShingle	DRNTU::Engineering::Electrical and electronic engineering::Computer hardware, software and systems Tan, Kian Huat. On extracting knowledge from neural networks
description	The primary contribution of the thesis is an algorithm that overcomes the significant limitations of previous methods by taking an approach to the task of extracting comprehensible rules from trained networks. This algorithm is called HyperNeuro. Given a neural network, HyperNeuro extracts linear if-then-else decision rules from trained neural networks that have been trained for classification problems..
author2	Chen, Yan Qiu
author_facet	Chen, Yan Qiu Tan, Kian Huat.
format	Theses and Dissertations
author	Tan, Kian Huat.
author_sort	Tan, Kian Huat.
title	On extracting knowledge from neural networks
title_short	On extracting knowledge from neural networks
title_full	On extracting knowledge from neural networks
title_fullStr	On extracting knowledge from neural networks
title_full_unstemmed	On extracting knowledge from neural networks
title_sort	on extracting knowledge from neural networks
publishDate	2008
url	http://hdl.handle.net/10356/3372
_version_	1772827735063789568

On extracting knowledge from neural networks

Similar Items