Self-adjusting feature maps network and its applications

Li, DL; Prasad, M; Lin, CT; Chang, JY

Self-adjusting feature maps network and its applications

Li, DL Prasad, M

Lin, CT

Chang, JY

Permalink

Publication Type:: Journal Article
Citation:: Neurocomputing, 2016, 207 pp. 78 - 94
Issue Date:: 2016-09-26

In Progress

	Filename	Description	Size
	[IJ7] Self-adjusting feature maps network and its applications.pdf	Accepted Manuscript	13.74 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is being processed and is not currently available.

Full metadata record

Field	Value	Language
dc.contributor.author	Li, DL	en_US
dc.contributor.author	Prasad, M https://orcid.org/0000-0001-9719-2253	en_US
dc.contributor.author	Lin, CT https://orcid.org/0000-0001-8371-8197	en_US
dc.contributor.author	Chang, JY	en_US
dc.date.issued	2016-09-26	en_US
dc.identifier.citation	Neurocomputing, 2016, 207 pp. 78 - 94	en_US
dc.identifier.issn	0925-2312	en_US
dc.identifier.uri	http://hdl.handle.net/10453/98712
dc.description.abstract	© 2016 Elsevier B.V. This paper, proposes a novel artificial neural network, called self-adjusting feature map (SAM), and develop its unsupervised learning ability with self-adjusting mechanism. The trained network structure of representative connected neurons not only displays the spatial relation of the input data distribution but also quantizes the data well. The SAM can automatically isolate a set of connected neurons, in which, the used number of the sets may indicate the number of clusters. The idea of self-adjusting mechanism is based on combining of mathematical statistics and neurological advantages and retreat of waste. In the training process, for each representative neuron has are three phases, growth, adaptation and decline. The network of representative neurons, first create the necessary neurons according to the local density of the input data in the growth phase. In the adaption phase, it adjusts neighborhood neuron pair׳s connected/disconnected topology constantly according to the statistics of input feature data. Finally, the unnecessary neurons of the network are merged or remove in the decline phase. In this paper, we exploit the SAM to handle some peculiar cases that cannot be handled easily by classical unsupervised learning networks such as self-organizing map (SOM) network. The remarkable characteristics of the SAM can be seen on various real world cases in the experimental results.	en_US
dc.relation.ispartof	Neurocomputing	en_US
dc.relation.isbasedon	10.1016/j.neucom.2016.03.067	en_US
dc.subject.classification	Artificial Intelligence & Image Processing	en_US
dc.title	Self-adjusting feature maps network and its applications	en_US
dc.type	Journal Article
utslib.citation.volume	207	en_US
utslib.for	080108 Neural, Evolutionary and Fuzzy Computation	en_US
utslib.for	08 Information and Computing Sciences	en_US
utslib.for	09 Engineering	en_US
utslib.for	17 Psychology and Cognitive Sciences	en_US
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Computer Science
pubs.organisational-group	/University of Technology Sydney/Strength - CAI - Centre for Artificial Intelligence
utslib.copyright.status	in_progress
pubs.publication-status	Published	en_US
pubs.volume	207	en_US

Abstract:

© 2016 Elsevier B.V. This paper, proposes a novel artificial neural network, called self-adjusting feature map (SAM), and develop its unsupervised learning ability with self-adjusting mechanism. The trained network structure of representative connected neurons not only displays the spatial relation of the input data distribution but also quantizes the data well. The SAM can automatically isolate a set of connected neurons, in which, the used number of the sets may indicate the number of clusters. The idea of self-adjusting mechanism is based on combining of mathematical statistics and neurological advantages and retreat of waste. In the training process, for each representative neuron has are three phases, growth, adaptation and decline. The network of representative neurons, first create the necessary neurons according to the local density of the input data in the growth phase. In the adaption phase, it adjusts neighborhood neuron pair׳s connected/disconnected topology constantly according to the statistics of input feature data. Finally, the unnecessary neurons of the network are merged or remove in the decline phase. In this paper, we exploit the SAM to handle some peculiar cases that cannot be handled easily by classical unsupervised learning networks such as self-organizing map (SOM) network. The remarkable characteristics of the SAM can be seen on various real world cases in the experimental results.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/98712