Bio-plausible digital implementation of a reward modulated STDP synapse
Reward-modulated Spike-Timing-Dependent Plasticity (R-STDP) is a learning method for Spiking Neural Network (SNN) that makes use of an external learning signal to modulate the synaptic plasticity produced by Spike-Timing-Dependent Plasticity (STDP). Combining the advantages of reinforcement learning...
Gespeichert in:
| Veröffentlicht in: | Neural computing & applications 2022-09, Vol.34 (18), p.15649-15660 |
|---|---|
| Hauptverfasser: | , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 15660 |
|---|---|
| container_issue | 18 |
| container_start_page | 15649 |
| container_title | Neural computing & applications |
| container_volume | 34 |
| creator | Quintana, Fernando M. Perez-Peña, Fernando Galindo, Pedro L. |
| description | Reward-modulated Spike-Timing-Dependent Plasticity (R-STDP) is a learning method for Spiking Neural Network (SNN) that makes use of an external learning signal to modulate the synaptic plasticity produced by Spike-Timing-Dependent Plasticity (STDP). Combining the advantages of reinforcement learning and the biological plausibility of STDP, online learning on SNN in real-world scenarios can be applied. This paper presents a fully digital architecture, implemented on an Field-Programmable Gate Array (FPGA), including the R-STDP learning mechanism in a SNN. The hardware results obtained are comparable to the software simulations results using the Brian2 simulator. The maximum error is of 0.083 when a 14-bits fix-point precision is used in realtime. The presented architecture shows an accuracy of 95% when tested in an obstacle avoidance problem on mobile robotics with a minimum use of resources. |
| doi_str_mv | 10.1007/s00521-022-07220-6 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2705906944</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2705906944</sourcerecordid><originalsourceid>FETCH-LOGICAL-c363t-7d6217d1c6e7ed3e5f7cd52d75968c2401d492759b30ab31ca1c8f38e3bdb7ad3</originalsourceid><addsrcrecordid>eNp9kE1LxDAQhoMouK7-AU8Bz9HJR5P2qKuuwoKC6zmkSbpk6ZdJi-y_t1rBm6dhmOd9Bx6ELilcUwB1kwAyRgkwRkAxBkQeoQUVnBMOWX6MFlCI6SwFP0VnKe0BQMg8W6D1XehIX5sxhbL22IVdGEyNQ9PXvvHtYIbQtbirsMHRf5rocNO5sTaDd_hte_-K06E1ffLn6KQydfIXv3OJ3h8ftqsnsnlZP69uN8RyyQeinGRUOWqlV95xn1XKuow5lRUyt0wAdaJg01ZyMCWn1lCbVzz3vHSlMo4v0dXc28fuY_Rp0PtujO30UjMFWQGyEGKi2EzZ2KUUfaX7GBoTD5qC_hamZ2F6EqZ_hGk5hfgcShPc7nz8q_4n9QVQ0G2b</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2705906944</pqid></control><display><type>article</type><title>Bio-plausible digital implementation of a reward modulated STDP synapse</title><source>SpringerLink Journals</source><creator>Quintana, Fernando M. ; Perez-Peña, Fernando ; Galindo, Pedro L.</creator><creatorcontrib>Quintana, Fernando M. ; Perez-Peña, Fernando ; Galindo, Pedro L.</creatorcontrib><description>Reward-modulated Spike-Timing-Dependent Plasticity (R-STDP) is a learning method for Spiking Neural Network (SNN) that makes use of an external learning signal to modulate the synaptic plasticity produced by Spike-Timing-Dependent Plasticity (STDP). Combining the advantages of reinforcement learning and the biological plausibility of STDP, online learning on SNN in real-world scenarios can be applied. This paper presents a fully digital architecture, implemented on an Field-Programmable Gate Array (FPGA), including the R-STDP learning mechanism in a SNN. The hardware results obtained are comparable to the software simulations results using the Brian2 simulator. The maximum error is of 0.083 when a 14-bits fix-point precision is used in realtime. The presented architecture shows an accuracy of 95% when tested in an obstacle avoidance problem on mobile robotics with a minimum use of resources.</description><identifier>ISSN: 0941-0643</identifier><identifier>EISSN: 1433-3058</identifier><identifier>DOI: 10.1007/s00521-022-07220-6</identifier><language>eng</language><publisher>London: Springer London</publisher><subject>Adaptation ; Artificial Intelligence ; Computational Biology/Bioinformatics ; Computational Science and Engineering ; Computer Science ; Data Mining and Knowledge Discovery ; Distance learning ; Dopamine ; Field programmable gate arrays ; Image Processing and Computer Vision ; Machine learning ; Neural networks ; Neurons ; Obstacle avoidance ; Original Article ; Probability and Statistics in Computer Science ; Robotics ; Software ; Teaching methods</subject><ispartof>Neural computing & applications, 2022-09, Vol.34 (18), p.15649-15660</ispartof><rights>The Author(s) 2022</rights><rights>The Author(s) 2022. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c363t-7d6217d1c6e7ed3e5f7cd52d75968c2401d492759b30ab31ca1c8f38e3bdb7ad3</citedby><cites>FETCH-LOGICAL-c363t-7d6217d1c6e7ed3e5f7cd52d75968c2401d492759b30ab31ca1c8f38e3bdb7ad3</cites><orcidid>0000-0001-5042-9399 ; 0000-0003-0892-8113 ; 0000-0003-3586-2930</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1007/s00521-022-07220-6$$EPDF$$P50$$Gspringer$$Hfree_for_read</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1007/s00521-022-07220-6$$EHTML$$P50$$Gspringer$$Hfree_for_read</linktohtml><link.rule.ids>314,776,780,27901,27902,41464,42533,51294</link.rule.ids></links><search><creatorcontrib>Quintana, Fernando M.</creatorcontrib><creatorcontrib>Perez-Peña, Fernando</creatorcontrib><creatorcontrib>Galindo, Pedro L.</creatorcontrib><title>Bio-plausible digital implementation of a reward modulated STDP synapse</title><title>Neural computing & applications</title><addtitle>Neural Comput & Applic</addtitle><description>Reward-modulated Spike-Timing-Dependent Plasticity (R-STDP) is a learning method for Spiking Neural Network (SNN) that makes use of an external learning signal to modulate the synaptic plasticity produced by Spike-Timing-Dependent Plasticity (STDP). Combining the advantages of reinforcement learning and the biological plausibility of STDP, online learning on SNN in real-world scenarios can be applied. This paper presents a fully digital architecture, implemented on an Field-Programmable Gate Array (FPGA), including the R-STDP learning mechanism in a SNN. The hardware results obtained are comparable to the software simulations results using the Brian2 simulator. The maximum error is of 0.083 when a 14-bits fix-point precision is used in realtime. The presented architecture shows an accuracy of 95% when tested in an obstacle avoidance problem on mobile robotics with a minimum use of resources.</description><subject>Adaptation</subject><subject>Artificial Intelligence</subject><subject>Computational Biology/Bioinformatics</subject><subject>Computational Science and Engineering</subject><subject>Computer Science</subject><subject>Data Mining and Knowledge Discovery</subject><subject>Distance learning</subject><subject>Dopamine</subject><subject>Field programmable gate arrays</subject><subject>Image Processing and Computer Vision</subject><subject>Machine learning</subject><subject>Neural networks</subject><subject>Neurons</subject><subject>Obstacle avoidance</subject><subject>Original Article</subject><subject>Probability and Statistics in Computer Science</subject><subject>Robotics</subject><subject>Software</subject><subject>Teaching methods</subject><issn>0941-0643</issn><issn>1433-3058</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>C6C</sourceid><sourceid>BENPR</sourceid><recordid>eNp9kE1LxDAQhoMouK7-AU8Bz9HJR5P2qKuuwoKC6zmkSbpk6ZdJi-y_t1rBm6dhmOd9Bx6ELilcUwB1kwAyRgkwRkAxBkQeoQUVnBMOWX6MFlCI6SwFP0VnKe0BQMg8W6D1XehIX5sxhbL22IVdGEyNQ9PXvvHtYIbQtbirsMHRf5rocNO5sTaDd_hte_-K06E1ffLn6KQydfIXv3OJ3h8ftqsnsnlZP69uN8RyyQeinGRUOWqlV95xn1XKuow5lRUyt0wAdaJg01ZyMCWn1lCbVzz3vHSlMo4v0dXc28fuY_Rp0PtujO30UjMFWQGyEGKi2EzZ2KUUfaX7GBoTD5qC_hamZ2F6EqZ_hGk5hfgcShPc7nz8q_4n9QVQ0G2b</recordid><startdate>20220901</startdate><enddate>20220901</enddate><creator>Quintana, Fernando M.</creator><creator>Perez-Peña, Fernando</creator><creator>Galindo, Pedro L.</creator><general>Springer London</general><general>Springer Nature B.V</general><scope>C6C</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>8FE</scope><scope>8FG</scope><scope>AFKRA</scope><scope>ARAPS</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>P5Z</scope><scope>P62</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><orcidid>https://orcid.org/0000-0001-5042-9399</orcidid><orcidid>https://orcid.org/0000-0003-0892-8113</orcidid><orcidid>https://orcid.org/0000-0003-3586-2930</orcidid></search><sort><creationdate>20220901</creationdate><title>Bio-plausible digital implementation of a reward modulated STDP synapse</title><author>Quintana, Fernando M. ; Perez-Peña, Fernando ; Galindo, Pedro L.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c363t-7d6217d1c6e7ed3e5f7cd52d75968c2401d492759b30ab31ca1c8f38e3bdb7ad3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Adaptation</topic><topic>Artificial Intelligence</topic><topic>Computational Biology/Bioinformatics</topic><topic>Computational Science and Engineering</topic><topic>Computer Science</topic><topic>Data Mining and Knowledge Discovery</topic><topic>Distance learning</topic><topic>Dopamine</topic><topic>Field programmable gate arrays</topic><topic>Image Processing and Computer Vision</topic><topic>Machine learning</topic><topic>Neural networks</topic><topic>Neurons</topic><topic>Obstacle avoidance</topic><topic>Original Article</topic><topic>Probability and Statistics in Computer Science</topic><topic>Robotics</topic><topic>Software</topic><topic>Teaching methods</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Quintana, Fernando M.</creatorcontrib><creatorcontrib>Perez-Peña, Fernando</creatorcontrib><creatorcontrib>Galindo, Pedro L.</creatorcontrib><collection>Springer Nature OA Free Journals</collection><collection>CrossRef</collection><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>ProQuest Central UK/Ireland</collection><collection>Advanced Technologies & Aerospace Collection</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>Advanced Technologies & Aerospace Database</collection><collection>ProQuest Advanced Technologies & Aerospace Collection</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><jtitle>Neural computing & applications</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Quintana, Fernando M.</au><au>Perez-Peña, Fernando</au><au>Galindo, Pedro L.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Bio-plausible digital implementation of a reward modulated STDP synapse</atitle><jtitle>Neural computing & applications</jtitle><stitle>Neural Comput & Applic</stitle><date>2022-09-01</date><risdate>2022</risdate><volume>34</volume><issue>18</issue><spage>15649</spage><epage>15660</epage><pages>15649-15660</pages><issn>0941-0643</issn><eissn>1433-3058</eissn><abstract>Reward-modulated Spike-Timing-Dependent Plasticity (R-STDP) is a learning method for Spiking Neural Network (SNN) that makes use of an external learning signal to modulate the synaptic plasticity produced by Spike-Timing-Dependent Plasticity (STDP). Combining the advantages of reinforcement learning and the biological plausibility of STDP, online learning on SNN in real-world scenarios can be applied. This paper presents a fully digital architecture, implemented on an Field-Programmable Gate Array (FPGA), including the R-STDP learning mechanism in a SNN. The hardware results obtained are comparable to the software simulations results using the Brian2 simulator. The maximum error is of 0.083 when a 14-bits fix-point precision is used in realtime. The presented architecture shows an accuracy of 95% when tested in an obstacle avoidance problem on mobile robotics with a minimum use of resources.</abstract><cop>London</cop><pub>Springer London</pub><doi>10.1007/s00521-022-07220-6</doi><tpages>12</tpages><orcidid>https://orcid.org/0000-0001-5042-9399</orcidid><orcidid>https://orcid.org/0000-0003-0892-8113</orcidid><orcidid>https://orcid.org/0000-0003-3586-2930</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0941-0643 |
| ispartof | Neural computing & applications, 2022-09, Vol.34 (18), p.15649-15660 |
| issn | 0941-0643 1433-3058 |
| language | eng |
| recordid | cdi_proquest_journals_2705906944 |
| source | SpringerLink Journals |
| subjects | Adaptation Artificial Intelligence Computational Biology/Bioinformatics Computational Science and Engineering Computer Science Data Mining and Knowledge Discovery Distance learning Dopamine Field programmable gate arrays Image Processing and Computer Vision Machine learning Neural networks Neurons Obstacle avoidance Original Article Probability and Statistics in Computer Science Robotics Software Teaching methods |
| title | Bio-plausible digital implementation of a reward modulated STDP synapse |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-11T04%3A22%3A05IST&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=Bio-plausible%20digital%20implementation%20of%20a%20reward%20modulated%20STDP%20synapse&rft.jtitle=Neural%20computing%20&%20applications&rft.au=Quintana,%20Fernando%20M.&rft.date=2022-09-01&rft.volume=34&rft.issue=18&rft.spage=15649&rft.epage=15660&rft.pages=15649-15660&rft.issn=0941-0643&rft.eissn=1433-3058&rft_id=info:doi/10.1007/s00521-022-07220-6&rft_dat=%3Cproquest_cross%3E2705906944%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2705906944&rft_id=info:pmid/&rfr_iscdi=true |