Please use this identifier to cite or link to this item:
https://hdl.handle.net/1959.11/5942
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Quah, Kian Hong | en |
dc.contributor.author | Quek, Hiok Chai | en |
dc.contributor.author | Leedham, Graham | en |
dc.date.accessioned | 2010-05-21T10:25:00Z | - |
dc.date.issued | 2005 | - |
dc.identifier.citation | Pattern Recognition, 38(4), p. 513-526 | en |
dc.identifier.issn | 1873-5142 | en |
dc.identifier.issn | 0031-3203 | en |
dc.identifier.uri | https://hdl.handle.net/1959.11/5942 | - |
dc.description.abstract | Reinforcement learning has been widely-used for applications in planning, control, and decision making. Rather than using instructive feedback as in supervised learning, reinforcement learning makes use of evaluative feedback to guide the learning process. In this paper, we formulate a pattern classification problem as a reinforcement learning problem. The problem is realized with a temporal difference method in a FALCON-R network. FALCON-R is constructed by integrating two basic FALCON-ART networks as function approximators, where one acts as a critic network (fuzzy predictor) and the other as an action network (fuzzy controller). This paper serves as a guideline in formulating a classification problem as a reinforcement learning problem using FALCON-R. The strengths of applying the reinforcement learning method to the pattern classification application are demonstrated. We show that such a system can converge faster, is able to escape from local minima, and has excellent disturbance rejection capability. | en |
dc.language | en | en |
dc.publisher | Elsevier Ltd | en |
dc.relation.ispartof | Pattern Recognition | en |
dc.title | Reinforcement learning combined with a fuzzy adaptive learning control network (FALCON-R) for pattern classification | en |
dc.type | Journal Article | en |
dc.identifier.doi | 10.1016/j.patcog.2004.08.011 | en |
dc.subject.keywords | Artificial Intelligence and Image Processing | en |
dc.subject.keywords | Computer Vision | en |
dc.subject.keywords | Image Processing | en |
local.contributor.firstname | Kian Hong | en |
local.contributor.firstname | Hiok Chai | en |
local.contributor.firstname | Graham | en |
local.subject.for2008 | 080104 Computer Vision | en |
local.subject.for2008 | 080106 Image Processing | en |
local.subject.for2008 | 080199 Artificial Intelligence and Image Processing not elsewhere classified | en |
local.subject.seo2008 | 810107 National Security | en |
local.subject.seo2008 | 890299 Computer Software and Services not elsewhere classified | en |
local.subject.seo2008 | 810199 Defence not elsewhere classified | en |
local.profile.school | School of Science and Technology | en |
local.profile.email | cleedham@une.edu.au | en |
local.output.category | C1 | en |
local.record.place | au | en |
local.record.institution | University of New England | en |
local.identifier.epublicationsrecord | une-20100415-134021 | en |
local.publisher.place | United Kingdom | en |
local.format.startpage | 513 | en |
local.format.endpage | 526 | en |
local.identifier.scopusid | 10644232306 | en |
local.peerreviewed | Yes | en |
local.identifier.volume | 38 | en |
local.identifier.issue | 4 | en |
local.contributor.lastname | Quah | en |
local.contributor.lastname | Quek | en |
local.contributor.lastname | Leedham | en |
dc.identifier.staff | une-id:cleedham | en |
local.profile.role | author | en |
local.profile.role | author | en |
local.profile.role | author | en |
local.identifier.unepublicationid | une:6086 | en |
dc.identifier.academiclevel | Academic | en |
local.title.maintitle | Reinforcement learning combined with a fuzzy adaptive learning control network (FALCON-R) for pattern classification | en |
local.output.categorydescription | C1 Refereed Article in a Scholarly Journal | en |
local.search.author | Quah, Kian Hong | en |
local.search.author | Quek, Hiok Chai | en |
local.search.author | Leedham, Graham | en |
local.uneassociation | Unknown | en |
local.year.published | 2005 | en |
Appears in Collections: | Journal Article School of Science and Technology |
Files in This Item:
File | Description | Size | Format |
---|
SCOPUSTM
Citations
17
checked on Nov 30, 2024
Page view(s)
1,152
checked on Feb 4, 2024
Download(s)
2
checked on Feb 4, 2024
Items in Research UNE are protected by copyright, with all rights reserved, unless otherwise indicated.