Unified formulation for training recurrent networks with derivative adaptive critics

We present a procedure for obtaining the derivatives used in training a recurrent network that combines in a unified framework the techniques of backpropagation through time and derivative adaptive critics. The resulting formulation is consistent with previous descriptions, but has the advantage of...

Full description

Saved in:
Bibliographic Details
Main Authors: Feldkamp, L.A., Puskorius, G.V., Prokhorov, D.V.
Format: Conference Proceeding
Language:English
Subjects:
Adaptive systems
Area measurement
Backpropagation
Computational intelligence
Dynamic programming
Equations
Laboratories
Learning
Neurodynamics
Programmable control
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page 2272 vol.4
container_issue
container_start_page 2268
container_title
container_volume 4
creator Feldkamp, L.A.
Puskorius, G.V.
Prokhorov, D.V.
description We present a procedure for obtaining the derivatives used in training a recurrent network that combines in a unified framework the techniques of backpropagation through time and derivative adaptive critics. The resulting formulation is consistent with previous descriptions, but has the advantage of allowing the mentioned techniques to be used together in a proportion that is appropriate to a given problem.
doi_str_mv 10.1109/ICNN.1997.614397
format conference_proceeding
fullrecord <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_614397</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>614397</ieee_id><sourcerecordid>614397</sourcerecordid><originalsourceid>FETCH-LOGICAL-i87t-b9810bd699bc5b201b5690fcbef21191839697850f65ed2b082c3b70029579ed3</originalsourceid><addsrcrecordid>eNotj8tOwzAURC0hJKB0j1j5BxL8SGLfJYp4VKrKJqyrOLmGC61TOW4r_p7QMps5i9FohrE7KXIpBTws6tUqlwAmr2ShwVywG2Gs0IVUyl6x-Th-iUlFWUAF16x5D-QJe-6HuN1v2kRD-GOeYkuBwgeP2O1jxJB4wHQc4vfIj5Q-eY-RDlP-gLzt290JukiJuvGWXfp2M-L832eseX5q6tds-fayqB-XGVmTMgdWCtdXAK4rnRLSlRUI3zn0SkqQVk8LjS2Fr0rslRNWddoZIRSUBrDXM3Z_riVEXO8ibdv4sz7f1r_eLU8t</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Unified formulation for training recurrent networks with derivative adaptive critics</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Feldkamp, L.A. ; Puskorius, G.V. ; Prokhorov, D.V.</creator><creatorcontrib>Feldkamp, L.A. ; Puskorius, G.V. ; Prokhorov, D.V.</creatorcontrib><description>We present a procedure for obtaining the derivatives used in training a recurrent network that combines in a unified framework the techniques of backpropagation through time and derivative adaptive critics. The resulting formulation is consistent with previous descriptions, but has the advantage of allowing the mentioned techniques to be used together in a proportion that is appropriate to a given problem.</description><identifier>ISBN: 0780341228</identifier><identifier>ISBN: 9780780341227</identifier><identifier>DOI: 10.1109/ICNN.1997.614397</identifier><language>eng</language><publisher>IEEE</publisher><subject>Adaptive systems ; Area measurement ; Backpropagation ; Computational intelligence ; Dynamic programming ; Equations ; Laboratories ; Learning ; Neurodynamics ; Programmable control</subject><ispartof>Proceedings of International Conference on Neural Networks (ICNN'97), 1997, Vol.4, p.2268-2272 vol.4</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/614397$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2058,4050,4051,27925,54920</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/614397$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Feldkamp, L.A.</creatorcontrib><creatorcontrib>Puskorius, G.V.</creatorcontrib><creatorcontrib>Prokhorov, D.V.</creatorcontrib><title>Unified formulation for training recurrent networks with derivative adaptive critics</title><title>Proceedings of International Conference on Neural Networks (ICNN'97)</title><addtitle>ICNN</addtitle><description>We present a procedure for obtaining the derivatives used in training a recurrent network that combines in a unified framework the techniques of backpropagation through time and derivative adaptive critics. The resulting formulation is consistent with previous descriptions, but has the advantage of allowing the mentioned techniques to be used together in a proportion that is appropriate to a given problem.</description><subject>Adaptive systems</subject><subject>Area measurement</subject><subject>Backpropagation</subject><subject>Computational intelligence</subject><subject>Dynamic programming</subject><subject>Equations</subject><subject>Laboratories</subject><subject>Learning</subject><subject>Neurodynamics</subject><subject>Programmable control</subject><isbn>0780341228</isbn><isbn>9780780341227</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>1997</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNotj8tOwzAURC0hJKB0j1j5BxL8SGLfJYp4VKrKJqyrOLmGC61TOW4r_p7QMps5i9FohrE7KXIpBTws6tUqlwAmr2ShwVywG2Gs0IVUyl6x-Th-iUlFWUAF16x5D-QJe-6HuN1v2kRD-GOeYkuBwgeP2O1jxJB4wHQc4vfIj5Q-eY-RDlP-gLzt290JukiJuvGWXfp2M-L832eseX5q6tds-fayqB-XGVmTMgdWCtdXAK4rnRLSlRUI3zn0SkqQVk8LjS2Fr0rslRNWddoZIRSUBrDXM3Z_riVEXO8ibdv4sz7f1r_eLU8t</recordid><startdate>1997</startdate><enddate>1997</enddate><creator>Feldkamp, L.A.</creator><creator>Puskorius, G.V.</creator><creator>Prokhorov, D.V.</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>1997</creationdate><title>Unified formulation for training recurrent networks with derivative adaptive critics</title><author>Feldkamp, L.A. ; Puskorius, G.V. ; Prokhorov, D.V.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i87t-b9810bd699bc5b201b5690fcbef21191839697850f65ed2b082c3b70029579ed3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>1997</creationdate><topic>Adaptive systems</topic><topic>Area measurement</topic><topic>Backpropagation</topic><topic>Computational intelligence</topic><topic>Dynamic programming</topic><topic>Equations</topic><topic>Laboratories</topic><topic>Learning</topic><topic>Neurodynamics</topic><topic>Programmable control</topic><toplevel>online_resources</toplevel><creatorcontrib>Feldkamp, L.A.</creatorcontrib><creatorcontrib>Puskorius, G.V.</creatorcontrib><creatorcontrib>Prokhorov, D.V.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE/IET Electronic Library</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Feldkamp, L.A.</au><au>Puskorius, G.V.</au><au>Prokhorov, D.V.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Unified formulation for training recurrent networks with derivative adaptive critics</atitle><btitle>Proceedings of International Conference on Neural Networks (ICNN'97)</btitle><stitle>ICNN</stitle><date>1997</date><risdate>1997</risdate><volume>4</volume><spage>2268</spage><epage>2272 vol.4</epage><pages>2268-2272 vol.4</pages><isbn>0780341228</isbn><isbn>9780780341227</isbn><abstract>We present a procedure for obtaining the derivatives used in training a recurrent network that combines in a unified framework the techniques of backpropagation through time and derivative adaptive critics. The resulting formulation is consistent with previous descriptions, but has the advantage of allowing the mentioned techniques to be used together in a proportion that is appropriate to a given problem.</abstract><pub>IEEE</pub><doi>10.1109/ICNN.1997.614397</doi></addata></record>
fulltext fulltext_linktorsrc
identifier ISBN: 0780341228
ispartof Proceedings of International Conference on Neural Networks (ICNN'97), 1997, Vol.4, p.2268-2272 vol.4
issn
language eng
recordid cdi_ieee_primary_614397
source IEEE Electronic Library (IEL) Conference Proceedings
subjects Adaptive systems
Area measurement
Backpropagation
Computational intelligence
Dynamic programming
Equations
Laboratories
Learning
Neurodynamics
Programmable control
title Unified formulation for training recurrent networks with derivative adaptive critics
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-04T23%3A02%3A30IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Unified%20formulation%20for%20training%20recurrent%20networks%20with%20derivative%20adaptive%20critics&rft.btitle=Proceedings%20of%20International%20Conference%20on%20Neural%20Networks%20(ICNN'97)&rft.au=Feldkamp,%20L.A.&rft.date=1997&rft.volume=4&rft.spage=2268&rft.epage=2272%20vol.4&rft.pages=2268-2272%20vol.4&rft.isbn=0780341228&rft.isbn_list=9780780341227&rft_id=info:doi/10.1109/ICNN.1997.614397&rft_dat=%3Cieee_6IE%3E614397%3C/ieee_6IE%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i87t-b9810bd699bc5b201b5690fcbef21191839697850f65ed2b082c3b70029579ed3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=614397&rfr_iscdi=true