{"id":"https://openalex.org/W7140330874","doi":"https://doi.org/10.48550/arxiv.2603.23206","title":"Latency Coding for Efficient and Low-Latency Deep Spiking Neural Networks","display_name":"Latency Coding for Efficient and Low-Latency Deep Spiking Neural Networks","publication_year":2026,"publication_date":"2026-03-24","ids":{"openalex":"https://openalex.org/W7140330874","doi":"https://doi.org/10.48550/arxiv.2603.23206"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.23206","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.23206","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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.2603.23206","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130608619","display_name":"Yi Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Yi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130546919","display_name":"Jianhao Ding","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ding, Jianhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5130566006","display_name":"Zhaofei Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Zhaofei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":0.8700000047683716,"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":0.8700000047683716,"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":0.05119999870657921,"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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.02710000053048134,"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/spiking-neural-network","display_name":"Spiking neural network","score":0.6736000180244446},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6657000184059143},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6546000242233276},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5338000059127808},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.4713999927043915},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.47110000252723694},{"id":"https://openalex.org/keywords/backpropagation","display_name":"Backpropagation","score":0.436599999666214},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.43160000443458557}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8004999756813049},{"id":"https://openalex.org/C11731999","wikidata":"https://www.wikidata.org/wiki/Q9067355","display_name":"Spiking neural network","level":3,"score":0.6736000180244446},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6657000184059143},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6546000242233276},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5338000059127808},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5156000256538391},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.4713999927043915},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.47110000252723694},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.436599999666214},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.43160000443458557},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.43160000443458557},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.39559999108314514},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.3598000109195709},{"id":"https://openalex.org/C77637269","wikidata":"https://www.wikidata.org/wiki/Q7002051","display_name":"Neural coding","level":2,"score":0.35830000042915344},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.3393999934196472},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.3353999853134155},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.328000009059906},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31310001015663147},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.31130000948905945},{"id":"https://openalex.org/C57890076","wikidata":"https://www.wikidata.org/wiki/Q4680725","display_name":"Adaptive coding","level":4,"score":0.2694999873638153},{"id":"https://openalex.org/C2779127903","wikidata":"https://www.wikidata.org/wiki/Q6510194","display_name":"Learning rule","level":3,"score":0.2694999873638153},{"id":"https://openalex.org/C134652429","wikidata":"https://www.wikidata.org/wiki/Q1052698","display_name":"Jitter","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.23206","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.23206","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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.2603.23206","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.23206","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.807550311088562}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Spiking":[0],"neural":[1,15,18],"networks":[2],"(SNNs)":[3],"offer":[4],"a":[5,34,81,104,143,206],"biologically":[6],"inspired":[7],"computing":[8],"paradigm":[9],"with":[10,109,179,183],"significant":[11],"potential":[12],"for":[13,211],"energy-efficient":[14,214],"processing.":[16,216],"Among":[17],"coding":[19,204],"schemes":[20],"of":[21,33,76,89,126],"SNNs,":[22],"Time-To-First-Spike":[23],"(TTFS)":[24],"coding,":[25,73,78],"which":[26],"encodes":[27],"information":[28,118,136],"through":[29,96],"the":[30,86,127,157,161],"precise":[31],"timing":[32],"neuron's":[35],"first":[36],"spike,":[37],"provides":[38],"exceptional":[39],"activity":[40],"sparsity":[41],"and":[42,58,79,112,138,141,165,187,208,213],"energy":[43,189],"efficiency.":[44,190],"However,":[45],"existing":[46,180],"TTFS":[47,77],"models":[48],"lack":[49],"efficient":[50,87],"training":[51,88],"methods,":[52],"suffering":[53],"from":[54],"high":[55,188],"inference":[56,185],"latency":[57,72,105,186,203],"limited":[59],"performance,":[60],"limiting":[61],"their":[62],"practicality":[63],"on":[64,156],"neuromorphic":[65,215],"hardware.":[66],"In":[67],"this":[68],"work,":[69],"we":[70],"propose":[71],"an":[74],"extension":[75],"present":[80],"compatible":[82],"framework":[83,101],"that":[84,150,170],"enables":[85],"deep":[90],"latency-coded":[91],"SNNs":[92,182,192],"by":[93],"leveraging":[94],"backpropagation":[95],"time":[97],"(BPTT)":[98],"algorithm.":[99],"The":[100],"includes:":[102],"(1)":[103],"encoding":[106],"(LE)":[107],"module":[108],"feature":[110],"extraction":[111],"straight-through":[113],"estimators":[114],"to":[115,134],"address":[116],"severe":[117],"loss":[119,148],"in":[120,131],"direct":[121],"intensity-to-latency":[122],"mapping;":[123],"(2)":[124],"relaxation":[125],"strict":[128],"single-spike":[129],"constraint":[130],"intermediate":[132],"layers":[133],"improve":[135],"propagation":[137],"gradient":[139],"flow;":[140],"(3)":[142],"temporal":[144],"adaptive":[145],"decision":[146],"(TAD)":[147],"function":[149],"dynamically":[151],"weights":[152],"supervision":[153],"signals":[154],"based":[155],"model's":[158],"confidence,":[159],"balancing":[160],"trade-off":[162],"between":[163],"speed":[164],"accuracy.":[166],"Experimental":[167],"results":[168],"demonstrate":[169,194],"our":[171],"method":[172],"achieves":[173],"competitive":[174],"or":[175],"superior":[176],"accuracy":[177],"compared":[178],"TTFS-coded":[181],"ultra-low":[184],"Latency-coded":[191],"also":[193],"improved":[195],"robustness":[196],"against":[197],"input":[198],"perturbations.":[199],"These":[200],"findings":[201],"highlight":[202],"as":[205],"practical":[207],"hardware-friendly":[209],"approach":[210],"fast":[212]},"counts_by_year":[],"updated_date":"2026-07-17T05:52:16.776730","created_date":"2026-03-26T00:00:00"}