{"id":"https://openalex.org/W7141311084","doi":"https://doi.org/10.48550/arxiv.2603.24891","title":"Surrogates, Spikes, and Sparsity: Performance Analysis and Characterization of SNN Hyperparameters on Hardware","display_name":"Surrogates, Spikes, and Sparsity: Performance Analysis and Characterization of SNN Hyperparameters on Hardware","publication_year":2026,"publication_date":"2026-03-26","ids":{"openalex":"https://openalex.org/W7141311084","doi":"https://doi.org/10.48550/arxiv.2603.24891"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.24891","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.24891","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.2603.24891","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009413114","display_name":"Ilkin Aliyev","orcid":"https://orcid.org/0009-0008-1719-2316"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aliyev, Ilkin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110909964","display_name":"Jes\u00fas G\u00e1mez L\u00f3pez","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lopez, Jesus","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5075537309","display_name":"Tosiron Adegbija","orcid":"https://orcid.org/0000-0002-2800-4834"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Adegbija, Tosiron","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":0.9706000089645386,"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":0.9706000089645386,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.01209999993443489,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.00800000037997961,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/spiking-neural-network","display_name":"Spiking neural network","score":0.5684999823570251},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.5601000189781189},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.49619999527931213},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.48010000586509705},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4505999982357025},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.36230000853538513},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.3416000008583069}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7742000222206116},{"id":"https://openalex.org/C11731999","wikidata":"https://www.wikidata.org/wiki/Q9067355","display_name":"Spiking neural network","level":3,"score":0.5684999823570251},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.5601000189781189},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.49619999527931213},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4812000095844269},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.48010000586509705},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4505999982357025},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41040000319480896},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.36230000853538513},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.3416000008583069},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.34049999713897705},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33959999680519104},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.328900009393692},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.29319998621940613},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.28760001063346863},{"id":"https://openalex.org/C134261354","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical inference","level":2,"score":0.2768999934196472},{"id":"https://openalex.org/C186565885","wikidata":"https://www.wikidata.org/wiki/Q1651163","display_name":"Biological neuron model","level":3,"score":0.27480000257492065},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C131675550","wikidata":"https://www.wikidata.org/wiki/Q7646884","display_name":"Surrogate model","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C2781390188","wikidata":"https://www.wikidata.org/wiki/Q25203449","display_name":"Spike (software development)","level":2,"score":0.26350000500679016}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.24891","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.24891","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.2603.24891","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.24891","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":0.894838809967041,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Spiking":[0],"Neural":[1],"Networks":[2],"(SNNs)":[3],"offer":[4],"inherent":[5],"advantages":[6],"for":[7,217],"low-power":[8],"inference":[9,110,147],"through":[10],"sparse,":[11],"event-driven":[12],"computation.":[13],"However,":[14],"the":[15,30,49,79,89,138],"theoretical":[16],"energy":[17],"benefits":[18],"of":[19,51,81,91,131],"SNNs":[20],"are":[21,128,229],"often":[22],"decoupled":[23],"from":[24,173,221],"real":[25],"hardware":[26,82,132,219],"performance":[27],"due":[28],"to":[29,84,151,175,180,210],"opaque":[31],"relationship":[32],"between":[33],"training-time":[34],"choices":[35],"and":[36,47,59,101,109,119,204,226],"inference-time":[37],"sparsity.":[38],"While":[39,134],"prior":[40],"work":[41],"has":[42],"focused":[43],"on":[44,106,141,153,186],"weight":[45],"pruning":[46],"compression,":[48],"role":[50],"training":[52,222],"hyperparameters":[53],"--":[54,63],"specifically":[55],"surrogate":[56,92],"gradient":[57,93],"functions":[58,94],"neuron":[60,102,163],"model":[61,164],"configurations":[62],"in":[64],"shaping":[65],"hardware-level":[66],"activation":[67],"sparsity":[68],"remains":[69],"underexplored.":[70],"This":[71],"paper":[72],"presents":[73],"a":[74,187,215],"workload":[75],"characterization":[76],"study":[77],"quantifying":[78],"sensitivity":[80],"latency":[83,148,182,205],"SNN":[85,191],"hyperparameters.":[86],"We":[87,159,184],"decouple":[88],"impact":[90],"(e.g.,":[95],"Fast":[96,135],"Sigmoid,":[97],"Spike":[98,143],"Rate":[99,144],"Escape)":[100],"models":[103],"(LIF,":[104],"Lapicque)":[105],"classification":[107],"accuracy":[108,126,140,157,201],"efficiency":[111],"across":[112],"three":[113],"event-based":[114],"vision":[115],"datasets:":[116],"DVS128-Gesture,":[117],"N-MNIST,":[118],"DVS-CIFAR10.":[120],"Our":[121],"analysis":[122],"reveals":[123],"that":[124,162,195],"standard":[125],"metrics":[127],"poor":[129],"predictors":[130],"efficiency.":[133],"Sigmoid":[136],"achieves":[137],"highest":[139],"DVS-CIFAR10,":[142],"Escape":[145],"reduces":[146],"by":[149,202,206],"up":[150,179],"12.2%":[152],"DVS128-Gesture":[154],"with":[155],"minimal":[156],"trade-offs.":[158],"also":[160],"demonstrate":[161],"selection":[165,198],"is":[166],"as":[167,169],"critical":[168],"parameter":[170],"tuning;":[171],"transitioning":[172],"LIF":[174],"Lapicque":[176],"neurons":[177],"yields":[178],"28%":[181],"reduction.":[183],"validate":[185],"custom":[188],"cycle-accurate":[189],"FPGA-based":[190],"instrumentation":[192],"platform,":[193],"showing":[194],"sparsity-aware":[196],"hyperparameter":[197],"can":[199],"improve":[200],"9.1%":[203],"over":[207],"2x":[208],"compared":[209],"baselines.":[211],"These":[212],"findings":[213],"establish":[214],"methodology":[216],"predicting":[218],"behavior":[220],"parameters.":[223],"The":[224],"RTL":[225],"reproducibility":[227],"artifacts":[228],"at":[230],"https://zenodo.org/records/18893738.":[231]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-03-28T00:00:00"}