{"id":"https://openalex.org/W7106114794","doi":"https://doi.org/10.48550/arxiv.2511.14691","title":"Attention via Synaptic Plasticity is All You Need: A Biologically Inspired Spiking Neuromorphic Transformer","display_name":"Attention via Synaptic Plasticity is All You Need: A Biologically Inspired Spiking Neuromorphic Transformer","publication_year":2025,"publication_date":"2025-11-18","ids":{"openalex":"https://openalex.org/W7106114794","doi":"https://doi.org/10.48550/arxiv.2511.14691"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2511.14691","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.14691","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2511.14691","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Mondal, Kallol","orcid":null},"institutions":[{"id":"https://openalex.org/I152869788","display_name":"Motilal Nehru National Institute of Technology","ror":"https://ror.org/04dp7tp96","country_code":"IN","type":"education","lineage":["https://openalex.org/I152869788"]},{"id":"https://openalex.org/I154851008","display_name":"Indian Institute of Technology Roorkee","ror":"https://ror.org/00582g326","country_code":"IN","type":"education","lineage":["https://openalex.org/I154851008"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Mondal, Kallol","raw_affiliation_strings":["Department of Electronics and Communication Engineering, National Institute of Technology Allahabad, Prayagraj","Centre for Nanotechnology, Indian Institute of Technology Roorkee"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronics and Communication Engineering, National Institute of Technology Allahabad, Prayagraj","institution_ids":["https://openalex.org/I152869788"]},{"raw_affiliation_string":"Centre for Nanotechnology, Indian Institute of Technology Roorkee","institution_ids":["https://openalex.org/I154851008"]}]},{"author_position":"last","author":{"id":null,"display_name":"Kumar, Ankush","orcid":null},"institutions":[{"id":"https://openalex.org/I154851008","display_name":"Indian Institute of Technology Roorkee","ror":"https://ror.org/00582g326","country_code":"IN","type":"education","lineage":["https://openalex.org/I154851008"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Kumar, Ankush","raw_affiliation_strings":["Centre for Nanotechnology, Indian Institute of Technology Roorkee"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Nanotechnology, Indian Institute of Technology Roorkee","institution_ids":["https://openalex.org/I154851008"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9049999713897705,"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":0.9049999713897705,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.06870000064373016,"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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.014100000262260437,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/neuromorphic-engineering","display_name":"Neuromorphic engineering","score":0.9110000133514404},{"id":"https://openalex.org/keywords/spiking-neural-network","display_name":"Spiking neural network","score":0.6366000175476074},{"id":"https://openalex.org/keywords/von-neumann-architecture","display_name":"Von Neumann architecture","score":0.5685999989509583},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5324000120162964},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5223000049591064},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.427700012922287},{"id":"https://openalex.org/keywords/synaptic-weight","display_name":"Synaptic weight","score":0.4138000011444092}],"concepts":[{"id":"https://openalex.org/C151927369","wikidata":"https://www.wikidata.org/wiki/Q1981312","display_name":"Neuromorphic engineering","level":3,"score":0.9110000133514404},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6930000185966492},{"id":"https://openalex.org/C11731999","wikidata":"https://www.wikidata.org/wiki/Q9067355","display_name":"Spiking neural network","level":3,"score":0.6366000175476074},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5839999914169312},{"id":"https://openalex.org/C80469333","wikidata":"https://www.wikidata.org/wiki/Q189088","display_name":"Von Neumann architecture","level":2,"score":0.5685999989509583},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5324000120162964},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5223000049591064},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.427700012922287},{"id":"https://openalex.org/C66949984","wikidata":"https://www.wikidata.org/wiki/Q7662043","display_name":"Synaptic weight","level":3,"score":0.4138000011444092},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.3871999979019165},{"id":"https://openalex.org/C98229152","wikidata":"https://www.wikidata.org/wiki/Q1551556","display_name":"Synaptic plasticity","level":3,"score":0.30640000104904175},{"id":"https://openalex.org/C150072547","wikidata":"https://www.wikidata.org/wiki/Q212923","display_name":"Memristor","level":2,"score":0.29589998722076416},{"id":"https://openalex.org/C48455012","wikidata":"https://www.wikidata.org/wiki/Q2892593","display_name":"Memory consolidation","level":3,"score":0.28380000591278076},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28360000252723694},{"id":"https://openalex.org/C2984127161","wikidata":"https://www.wikidata.org/wiki/Q969316","display_name":"Neural activity","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C159919123","wikidata":"https://www.wikidata.org/wiki/Q7577157","display_name":"Spike-timing-dependent plasticity","level":4,"score":0.26330000162124634},{"id":"https://openalex.org/C15286952","wikidata":"https://www.wikidata.org/wiki/Q8037925","display_name":"Computational neuroscience","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C3832189","wikidata":"https://www.wikidata.org/wiki/Q8588916","display_name":"Models of neural computation","level":3,"score":0.2540000081062317}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2511.14691","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.14691","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2511.14691","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.14691","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"score":0.7685334086418152,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Attention":[0],"is":[1],"the":[2,21,39,70,94,124,144,174,224],"brain's":[3],"ability":[4],"to":[5,48,66,84,111,216,227],"selectively":[6],"focus":[7],"on":[8,63,90,105,209],"a":[9,49,81,149,166,217],"few":[10],"specific":[11],"aspects":[12],"while":[13],"ignoring":[14],"irrelevant":[15],"ones.":[16],"This":[17],"biological":[18],"principle":[19],"inspired":[20,238],"attention":[22,55,61,96,102,119,239],"mechanism":[23,168],"in":[24,69,162,173,179],"modern":[25],"Transformers.":[26],"Transformers":[27],"now":[28],"underpin":[29],"large":[30,50],"language":[31],"models":[32],"(LLMs)":[33],"such":[34],"as":[35],"GPT,":[36],"but":[37],"at":[38],"cost":[40],"of":[41,169],"massive":[42],"training":[43],"and":[44,131,171,176,186,193,199,206,244],"inference":[45],"energy,":[46],"leading":[47],"carbon":[51],"footprint.":[52],"While":[53],"brain":[54,175],"emerges":[56],"from":[57,123,135],"neural":[58,77],"circuits,":[59],"Transformer":[60,147,151],"relies":[62,104],"dot-product":[64,106],"similarity":[65,109],"weight":[67],"elements":[68],"input":[71],"sequence.":[72],"Neuromorphic":[73],"computing,":[74],"especially":[75],"spiking":[76,92,101],"networks":[78],"(SNNs),":[79],"offers":[80],"brain-inspired":[82],"path":[83],"energy-efficient":[85],"intelligence.":[86],"Despite":[87],"recent":[88],"work":[89],"attention-based":[91],"Transformers,":[93],"core":[95,167],"layer":[97],"remains":[98],"non-neuromorphic.":[99],"Current":[100],"(i)":[103],"or":[107],"element-wise":[108],"suited":[110],"floating-point":[112],"operations,":[113],"not":[114],"event-driven":[115],"spikes;":[116],"(ii)":[117],"keeps":[118],"matrices":[120],"that":[121,152,223],"suffer":[122],"von":[125],"Neumann":[126,189],"bottleneck,":[127],"limiting":[128],"in-memory":[129,184],"computing;":[130],"(iii)":[132],"still":[133],"diverges":[134],"brain-like":[136],"computation.":[137],"To":[138],"address":[139],"these":[140],"issues,":[141],"we":[142],"propose":[143],"Spiking":[145],"STDP":[146],"(S$^{2}$TDPT),":[148],"neuromorphic":[150,180,246],"implements":[153],"self-attention":[154],"through":[155],"spike-timing-dependent":[156],"plasticity":[157],"(STDP),":[158],"embedding":[159],"query--key":[160],"correlations":[161],"synaptic":[163],"weights.":[164],"STDP,":[165],"memory":[170],"learning":[172],"widely":[177],"studied":[178],"devices,":[181],"naturally":[182],"enables":[183],"computing":[185],"supports":[187],"non-von":[188],"hardware.":[190],"On":[191],"CIFAR-10":[192],"CIFAR-100,":[194,210],"our":[195],"model":[196,225],"achieves":[197],"94.35\\%":[198],"78.08\\%":[200],"accuracy":[201],"with":[202],"only":[203],"four":[204],"timesteps":[205],"0.49":[207],"mJ":[208],"an":[211],"88.47\\%":[212],"energy":[213],"reduction":[214],"compared":[215],"standard":[218],"ANN":[219],"Transformer.":[220],"Grad-CAM":[221],"shows":[222],"attends":[226],"semantically":[228],"relevant":[229],"regions,":[230],"enhancing":[231],"interpretability.":[232],"Overall,":[233],"S$^{2}$TDPT":[234],"illustrates":[235],"how":[236],"biologically":[237],"can":[240],"yield":[241],"energy-efficient,":[242],"hardware-friendly,":[243],"explainable":[245],"models.":[247]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-11-20T00:00:00"}