Loading…

Stand-alone hardware-based learning system

The probabilistic Random Access Memory (pRAM) is a biologically-inspired model of a neuron. The pRAM behaviour is described in this paper in relation to binary and real-valued input vectors. The pRAM is hardware-realisable, as is its reinforcement training algorithm. The pRAM model may be applied to...

Full description

Saved in:
Bibliographic Details
Published in:Japanese Journal of Applied Physics 1995-02, Vol.34 (2B), p.1050-1055
Main Authors: CLARKSON, T, CHI KWONG NG
Format: Article
Language:English
Subjects:
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page 1055
container_issue 2B
container_start_page 1050
container_title Japanese Journal of Applied Physics
container_volume 34
creator CLARKSON, T
CHI KWONG NG
description The probabilistic Random Access Memory (pRAM) is a biologically-inspired model of a neuron. The pRAM behaviour is described in this paper in relation to binary and real-valued input vectors. The pRAM is hardware-realisable, as is its reinforcement training algorithm. The pRAM model may be applied to a wide range of artificial neural network applications, many of which are classification tasks. The application presented here is a control problem where an inverted pendulum, mounted on a cart, is to be balanced. The solution to this problem using the pRAM-256, a VLSI pRAM controller, is shown.
doi_str_mv 10.1143/JJAP.34.1050
format article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_26004290</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>26004290</sourcerecordid><originalsourceid>FETCH-LOGICAL-c373t-e7a47d419cfdb242896c79903ad85f01fb0dfda97bd658d6998111f09d5063f33</originalsourceid><addsrcrecordid>eNo9kEtLw0AUhQdRsFZ3_oAuxIU49c4zmWUpvkpBQV0PN_PQSJrUmRTpvzelxdXhwDnf4iPkksGUMSnuFovZ61TIKQMFR2TEhCyoBK2OyQiAMyoN56fkLOfvoWol2YjcvPXYeopN14bJFyb_iynQCnPwkyZgauv2c5K3uQ-rc3ISscnh4pBj8vFw_z5_osuXx-f5bEmdKERPQ4Gy8JIZF33FJS-NdoUxINCXKgKLFfjo0RSV16r02piSMRbBeAVaRCHG5HrPXafuZxNyb1d1dqFpsA3dJluuASQfgGNyux-61OWcQrTrVK8wbS0DuxNid0KskHYnZJhfHbiYHTYxYevq_P8ZZCmplfgDFJxedw</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>26004290</pqid></control><display><type>article</type><title>Stand-alone hardware-based learning system</title><source>Institute of Physics</source><source>Institute of Physics:Jisc Collections:IOP Publishing Read and Publish 2024-2025 (Reading List)</source><creator>CLARKSON, T ; CHI KWONG NG</creator><creatorcontrib>CLARKSON, T ; CHI KWONG NG</creatorcontrib><description>The probabilistic Random Access Memory (pRAM) is a biologically-inspired model of a neuron. The pRAM behaviour is described in this paper in relation to binary and real-valued input vectors. The pRAM is hardware-realisable, as is its reinforcement training algorithm. The pRAM model may be applied to a wide range of artificial neural network applications, many of which are classification tasks. The application presented here is a control problem where an inverted pendulum, mounted on a cart, is to be balanced. The solution to this problem using the pRAM-256, a VLSI pRAM controller, is shown.</description><identifier>ISSN: 0021-4922</identifier><identifier>EISSN: 1347-4065</identifier><identifier>DOI: 10.1143/JJAP.34.1050</identifier><identifier>CODEN: JJAPA5</identifier><language>eng</language><publisher>Tokyo: Japanese journal of applied physics</publisher><subject>Applied sciences ; Electric, optical and optoelectronic circuits ; Electronics ; Exact sciences and technology ; Neural networks</subject><ispartof>Japanese Journal of Applied Physics, 1995-02, Vol.34 (2B), p.1050-1055</ispartof><rights>1995 INIST-CNRS</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>309,310,314,776,780,785,786,23909,23910,25118,27901,27902</link.rule.ids><backlink>$$Uhttp://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&amp;idt=3475465$$DView record in Pascal Francis$$Hfree_for_read</backlink></links><search><creatorcontrib>CLARKSON, T</creatorcontrib><creatorcontrib>CHI KWONG NG</creatorcontrib><title>Stand-alone hardware-based learning system</title><title>Japanese Journal of Applied Physics</title><description>The probabilistic Random Access Memory (pRAM) is a biologically-inspired model of a neuron. The pRAM behaviour is described in this paper in relation to binary and real-valued input vectors. The pRAM is hardware-realisable, as is its reinforcement training algorithm. The pRAM model may be applied to a wide range of artificial neural network applications, many of which are classification tasks. The application presented here is a control problem where an inverted pendulum, mounted on a cart, is to be balanced. The solution to this problem using the pRAM-256, a VLSI pRAM controller, is shown.</description><subject>Applied sciences</subject><subject>Electric, optical and optoelectronic circuits</subject><subject>Electronics</subject><subject>Exact sciences and technology</subject><subject>Neural networks</subject><issn>0021-4922</issn><issn>1347-4065</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>1995</creationdate><recordtype>article</recordtype><recordid>eNo9kEtLw0AUhQdRsFZ3_oAuxIU49c4zmWUpvkpBQV0PN_PQSJrUmRTpvzelxdXhwDnf4iPkksGUMSnuFovZ61TIKQMFR2TEhCyoBK2OyQiAMyoN56fkLOfvoWol2YjcvPXYeopN14bJFyb_iynQCnPwkyZgauv2c5K3uQ-rc3ISscnh4pBj8vFw_z5_osuXx-f5bEmdKERPQ4Gy8JIZF33FJS-NdoUxINCXKgKLFfjo0RSV16r02piSMRbBeAVaRCHG5HrPXafuZxNyb1d1dqFpsA3dJluuASQfgGNyux-61OWcQrTrVK8wbS0DuxNid0KskHYnZJhfHbiYHTYxYevq_P8ZZCmplfgDFJxedw</recordid><startdate>19950201</startdate><enddate>19950201</enddate><creator>CLARKSON, T</creator><creator>CHI KWONG NG</creator><general>Japanese journal of applied physics</general><scope>IQODW</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>8FD</scope><scope>H8D</scope><scope>L7M</scope></search><sort><creationdate>19950201</creationdate><title>Stand-alone hardware-based learning system</title><author>CLARKSON, T ; CHI KWONG NG</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c373t-e7a47d419cfdb242896c79903ad85f01fb0dfda97bd658d6998111f09d5063f33</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>1995</creationdate><topic>Applied sciences</topic><topic>Electric, optical and optoelectronic circuits</topic><topic>Electronics</topic><topic>Exact sciences and technology</topic><topic>Neural networks</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>CLARKSON, T</creatorcontrib><creatorcontrib>CHI KWONG NG</creatorcontrib><collection>Pascal-Francis</collection><collection>CrossRef</collection><collection>Technology Research Database</collection><collection>Aerospace Database</collection><collection>Advanced Technologies Database with Aerospace</collection><jtitle>Japanese Journal of Applied Physics</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>CLARKSON, T</au><au>CHI KWONG NG</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Stand-alone hardware-based learning system</atitle><jtitle>Japanese Journal of Applied Physics</jtitle><date>1995-02-01</date><risdate>1995</risdate><volume>34</volume><issue>2B</issue><spage>1050</spage><epage>1055</epage><pages>1050-1055</pages><issn>0021-4922</issn><eissn>1347-4065</eissn><coden>JJAPA5</coden><abstract>The probabilistic Random Access Memory (pRAM) is a biologically-inspired model of a neuron. The pRAM behaviour is described in this paper in relation to binary and real-valued input vectors. The pRAM is hardware-realisable, as is its reinforcement training algorithm. The pRAM model may be applied to a wide range of artificial neural network applications, many of which are classification tasks. The application presented here is a control problem where an inverted pendulum, mounted on a cart, is to be balanced. The solution to this problem using the pRAM-256, a VLSI pRAM controller, is shown.</abstract><cop>Tokyo</cop><pub>Japanese journal of applied physics</pub><doi>10.1143/JJAP.34.1050</doi><tpages>6</tpages></addata></record>
fulltext fulltext
identifier ISSN: 0021-4922
ispartof Japanese Journal of Applied Physics, 1995-02, Vol.34 (2B), p.1050-1055
issn 0021-4922
1347-4065
language eng
recordid cdi_proquest_miscellaneous_26004290
source Institute of Physics; Institute of Physics:Jisc Collections:IOP Publishing Read and Publish 2024-2025 (Reading List)
subjects Applied sciences
Electric, optical and optoelectronic circuits
Electronics
Exact sciences and technology
Neural networks
title Stand-alone hardware-based learning system
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-16T01%3A55%3A39IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Stand-alone%20hardware-based%20learning%20system&rft.jtitle=Japanese%20Journal%20of%20Applied%20Physics&rft.au=CLARKSON,%20T&rft.date=1995-02-01&rft.volume=34&rft.issue=2B&rft.spage=1050&rft.epage=1055&rft.pages=1050-1055&rft.issn=0021-4922&rft.eissn=1347-4065&rft.coden=JJAPA5&rft_id=info:doi/10.1143/JJAP.34.1050&rft_dat=%3Cproquest_cross%3E26004290%3C/proquest_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c373t-e7a47d419cfdb242896c79903ad85f01fb0dfda97bd658d6998111f09d5063f33%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=26004290&rft_id=info:pmid/&rfr_iscdi=true