{"id":"https://openalex.org/W3174379061","doi":"https://doi.org/10.1109/aicas51828.2021.9458560","title":"Hardware Approximation of Exponential Decay for Spiking Neural Networks","display_name":"Hardware Approximation of Exponential Decay for Spiking Neural Networks","publication_year":2021,"publication_date":"2021-06-06","ids":{"openalex":"https://openalex.org/W3174379061","doi":"https://doi.org/10.1109/aicas51828.2021.9458560","mag":"3174379061"},"language":"en","primary_location":{"id":"doi:10.1109/aicas51828.2021.9458560","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aicas51828.2021.9458560","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 3rd International Conference on Artificial Intelligence Circuits and Systems (AICAS)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pure.tue.nl/ws/files/174611165/Approximating_decay_functions_in_Spiking_Neural_Networks_Implementation_and_Effect_22_.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103231577","display_name":"Sherif Eissa","orcid":"https://orcid.org/0000-0001-8210-2323"},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Sherif Eissa","raw_affiliation_strings":["Eindhoven University of Technology, Eindhoven, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Eindhoven University of Technology, Eindhoven, The Netherlands","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032436846","display_name":"Sander Stuijk","orcid":"https://orcid.org/0000-0002-2518-6847"},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Sander Stuijk","raw_affiliation_strings":["Eindhoven University of Technology, Eindhoven, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Eindhoven University of Technology, Eindhoven, The Netherlands","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081768631","display_name":"Henk Corporaal","orcid":"https://orcid.org/0000-0003-4506-5732"},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Henk Corporaal","raw_affiliation_strings":["Eindhoven University of Technology, Eindhoven, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Eindhoven University of Technology, Eindhoven, The Netherlands","institution_ids":["https://openalex.org/I83019370"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5103231577"],"corresponding_institution_ids":["https://openalex.org/I83019370"],"apc_list":null,"apc_paid":null,"fwci":0.5078,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.63881219,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10581","display_name":"Neural dynamics and brain function","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11601","display_name":"Neuroscience and Neural Engineering","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/2804","display_name":"Cellular and Molecular Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/exponential-function","display_name":"Exponential function","score":0.601119875907898},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5631409883499146},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.548407793045044},{"id":"https://openalex.org/keywords/exponential-decay","display_name":"Exponential decay","score":0.4505045711994171},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3917224407196045},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.25574246048927307},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.20252683758735657},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.13696622848510742},{"id":"https://openalex.org/keywords/nuclear-physics","display_name":"Nuclear physics","score":0.13095247745513916}],"concepts":[{"id":"https://openalex.org/C151376022","wikidata":"https://www.wikidata.org/wiki/Q168698","display_name":"Exponential function","level":2,"score":0.601119875907898},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5631409883499146},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.548407793045044},{"id":"https://openalex.org/C180188523","wikidata":"https://www.wikidata.org/wiki/Q574576","display_name":"Exponential decay","level":2,"score":0.4505045711994171},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3917224407196045},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25574246048927307},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.20252683758735657},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.13696622848510742},{"id":"https://openalex.org/C185544564","wikidata":"https://www.wikidata.org/wiki/Q81197","display_name":"Nuclear physics","level":1,"score":0.13095247745513916}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/aicas51828.2021.9458560","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aicas51828.2021.9458560","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 3rd International Conference on Artificial Intelligence Circuits and Systems (AICAS)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.tue.nl:openaire/ee9369b7-709e-45f5-b7c0-e7e5f158b31a","is_oa":true,"landing_page_url":"https://research.tue.nl/en/publications/ee9369b7-709e-45f5-b7c0-e7e5f158b31a","pdf_url":"https://pure.tue.nl/ws/files/174611165/Approximating_decay_functions_in_Spiking_Neural_Networks_Implementation_and_Effect_22_.pdf","source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Eissa, S, Stuijk, S & Corporaal, H 2021, Hardware Approximation of Exponential Decay for Spiking Neural Networks. in 2021 IEEE 3rd International Conference on Artificial Intelligence Circuits and Systems, AICAS 2021., 9458560, Institute of Electrical and Electronics Engineers, 3rd IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2021, Washington, District of Columbia, United States, 3/05/21. https://doi.org/10.1109/AICAS51828.2021.9458560","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:pure.tue.nl:publications/ee9369b7-709e-45f5-b7c0-e7e5f158b31a","is_oa":true,"landing_page_url":"http://www.scopus.com/inward/record.url?scp=85113292007&partnerID=8YFLogxK","pdf_url":null,"source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Eissa, S, Stuijk, S & Corporaal, H 2021, Hardware Approximation of Exponential Decay for Spiking Neural Networks. in 2021 IEEE 3rd International Conference on Artificial Intelligence Circuits and Systems, AICAS 2021., 9458560, Institute of Electrical and Electronics Engineers, 3rd IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2021, Washington, District of Columbia, United States, 3/05/21. https://doi.org/10.1109/AICAS51828.2021.9458560","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:tue:oai:pure.tue.nl:publications/ee9369b7-709e-45f5-b7c0-e7e5f158b31a","is_oa":true,"landing_page_url":"https://research.tue.nl/nl/publications/ee9369b7-709e-45f5-b7c0-e7e5f158b31a","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2021 IEEE 3rd International Conference on Artificial Intelligence Circuits and Systems, AICAS 2021","raw_type":"info:eu-repo/semantics/conferencepaper"}],"best_oa_location":{"id":"pmh:oai:pure.tue.nl:openaire/ee9369b7-709e-45f5-b7c0-e7e5f158b31a","is_oa":true,"landing_page_url":"https://research.tue.nl/en/publications/ee9369b7-709e-45f5-b7c0-e7e5f158b31a","pdf_url":"https://pure.tue.nl/ws/files/174611165/Approximating_decay_functions_in_Spiking_Neural_Networks_Implementation_and_Effect_22_.pdf","source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Eissa, S, Stuijk, S & Corporaal, H 2021, Hardware Approximation of Exponential Decay for Spiking Neural Networks. in 2021 IEEE 3rd International Conference on Artificial Intelligence Circuits and Systems, AICAS 2021., 9458560, Institute of Electrical and Electronics Engineers, 3rd IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2021, Washington, District of Columbia, United States, 3/05/21. https://doi.org/10.1109/AICAS51828.2021.9458560","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.9100000262260437,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3174379061.pdf","grobid_xml":"https://content.openalex.org/works/W3174379061.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1484977481","https://openalex.org/W1686810756","https://openalex.org/W2010069327","https://openalex.org/W2112796928","https://openalex.org/W2194775991","https://openalex.org/W2528063041","https://openalex.org/W2760393804","https://openalex.org/W2783525259","https://openalex.org/W2902963085","https://openalex.org/W2903455717","https://openalex.org/W2904620099","https://openalex.org/W2962835968","https://openalex.org/W2963834742","https://openalex.org/W2971601850","https://openalex.org/W2980513133","https://openalex.org/W3007283957","https://openalex.org/W3015205410","https://openalex.org/W3035008388","https://openalex.org/W3036270242","https://openalex.org/W3042066834","https://openalex.org/W3046044791","https://openalex.org/W3118608800","https://openalex.org/W3190686567","https://openalex.org/W4231081240","https://openalex.org/W4298355310","https://openalex.org/W6637373629","https://openalex.org/W6652670974","https://openalex.org/W6749922295","https://openalex.org/W6756520512","https://openalex.org/W6757028267","https://openalex.org/W6779701982"],"related_works":["https://openalex.org/W4378446382","https://openalex.org/W2004451688","https://openalex.org/W2042975291","https://openalex.org/W1980067290","https://openalex.org/W2243342443","https://openalex.org/W4248539579","https://openalex.org/W1916647340","https://openalex.org/W1990926383","https://openalex.org/W1667590769","https://openalex.org/W2085263497"],"abstract_inverted_index":{"Spiking":[0],"neural":[1,41],"networks":[2,125],"(SNNs)":[3],"may":[4],"enable":[5],"low-power":[6],"intelligence":[7],"on":[8,56,64,123],"the":[9,13,19,24,60,68,78,132],"edge":[10],"by":[11,85],"combining":[12],"merits":[14],"of":[15,29,59,80,110,163],"deep":[16],"learning":[17],"with":[18,107],"computational":[20],"paradigms":[21],"found":[22],"in":[23,83,113],"human":[25],"neo-cortex.":[26],"The":[27],"choice":[28],"neuron":[30],"model":[31],"is":[32],"an":[33],"open":[34],"research":[35],"topic.":[36],"Many":[37],"spiking":[38],"models":[39],"implement":[40],"dynamics":[42],"from":[43],"biology":[44],"that":[45],"involve":[46],"one":[47],"or":[48],"more":[49],"exponential":[50,61,89],"decay":[51,62,90],"functions.":[52],"Previous":[53],"work":[54],"focused":[55],"accurate":[57],"modeling":[58],"function":[63],"neuromorphic":[65],"hardware":[66,118,141],"to":[67,153],"last":[69],"significant":[70],"bit":[71,98],"(LSB).":[72],"In":[73],"this":[74],"paper,":[75],"we":[76,135],"explore":[77],"limits":[79],"error":[81],"resilience":[82,152],"SNNs":[84],"aggressively":[86],"approximating":[87],"their":[88],"functions":[91],"and":[92,105,120,126,158],"allowing":[93],"for":[94,143],"losses":[95],"within":[96],"our":[97],"precision.":[99],"Three":[100],"approximation":[101],"methods":[102],"are":[103,128],"presented":[104],"implemented":[106,136],"varying":[108],"degrees":[109],"precision":[111],"resulting":[112],"10":[114],"different":[115],"implementations.":[116],"Their":[117],"cost":[119],"inference":[121,133],"accuracy":[122],"benchmark":[124],"applications":[127],"compared.":[129],"To":[130],"improve":[131],"accuracy,":[134],"fine-tuning.":[137],"We":[138],"also":[139],"introduced":[140],"programmability":[142],"certain":[144],"time":[145],"constants":[146],"as":[147],"hyperparameters.":[148],"Our":[149],"results":[150],"show":[151],"lossy":[154],"approximation,":[155],"fast":[156],"fine-tuning,":[157],"a":[159],"low":[160],"energy":[161],"consumption":[162],"47":[164],"fJ":[165],"per":[166],"operation.":[167]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}