{"id":"https://openalex.org/W7162461299","doi":"https://doi.org/10.1109/ispass69572.2026.00063","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":"2026-04-26","ids":{"openalex":"https://openalex.org/W7162461299","doi":"https://doi.org/10.1109/ispass69572.2026.00063"},"language":null,"primary_location":{"id":"doi:10.1109/ispass69572.2026.00063","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispass69572.2026.00063","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009413114","display_name":"Ilkin Aliyev","orcid":"https://orcid.org/0009-0008-1719-2316"},"institutions":[{"id":"https://openalex.org/I138006243","display_name":"University of Arizona","ror":"https://ror.org/03m2x1q45","country_code":"US","type":"education","lineage":["https://openalex.org/I138006243"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ilkin Aliyev","raw_affiliation_strings":["The University of Arizona,Department of Electrical and Computer Engineering,Tucson,AZ,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Arizona,Department of Electrical and Computer Engineering,Tucson,AZ,USA","institution_ids":["https://openalex.org/I138006243"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137002351","display_name":"Jesus Lopez","orcid":null},"institutions":[{"id":"https://openalex.org/I138006243","display_name":"University of Arizona","ror":"https://ror.org/03m2x1q45","country_code":"US","type":"education","lineage":["https://openalex.org/I138006243"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jesus Lopez","raw_affiliation_strings":["The University of Arizona,Department of Electrical and Computer Engineering,Tucson,AZ,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Arizona,Department of Electrical and Computer Engineering,Tucson,AZ,USA","institution_ids":["https://openalex.org/I138006243"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075537309","display_name":"Tosiron Adegbija","orcid":"https://orcid.org/0000-0002-2800-4834"},"institutions":[{"id":"https://openalex.org/I138006243","display_name":"University of Arizona","ror":"https://ror.org/03m2x1q45","country_code":"US","type":"education","lineage":["https://openalex.org/I138006243"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tosiron Adegbija","raw_affiliation_strings":["The University of Arizona,Department of Electrical and Computer Engineering,Tucson,AZ,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Arizona,Department of Electrical and Computer Engineering,Tucson,AZ,USA","institution_ids":["https://openalex.org/I138006243"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I138006243"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.50293454,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"601","last_page":"613"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.10660000145435333,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.10660000145435333,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.08669999986886978,"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"}},{"id":"https://openalex.org/T10951","display_name":"Cryptographic Implementations and Security","score":0.06689999997615814,"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/characterization","display_name":"Characterization (materials science)","score":0.39730000495910645},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37209999561309814},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.3294999897480011},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.296999990940094},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.25690001249313354}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6746000051498413},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5081999897956848},{"id":"https://openalex.org/C2780841128","wikidata":"https://www.wikidata.org/wiki/Q5073781","display_name":"Characterization (materials science)","level":2,"score":0.39730000495910645},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3779999911785126},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37209999561309814},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.3294999897480011},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.296999990940094},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2621000111103058},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ispass69572.2026.00063","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispass69572.2026.00063","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2098328927","https://openalex.org/W2939020224","https://openalex.org/W2949676527","https://openalex.org/W2984844508","https://openalex.org/W3139657805","https://openalex.org/W3201870057","https://openalex.org/W4231081240","https://openalex.org/W4280505862","https://openalex.org/W4285247025","https://openalex.org/W4308479820","https://openalex.org/W4312348535","https://openalex.org/W4313191607","https://openalex.org/W4385187422","https://openalex.org/W4385482698","https://openalex.org/W4392822827","https://openalex.org/W4396680641","https://openalex.org/W4400231188","https://openalex.org/W4401568185","https://openalex.org/W4404411631","https://openalex.org/W4404688456","https://openalex.org/W4404954477","https://openalex.org/W4409248468"],"related_works":[],"abstract_inverted_index":{"Spiking":[0],"Neural":[1],"Networks":[2],"(SNNs)":[3],"offer":[4],"inherent":[5],"advantages":[6],"for":[7,230],"low-power":[8],"inference":[9,108,148],"through":[10],"sparse,":[11],"event-driven":[12],"computation.":[13],"However,":[14],"the":[15,30,50,77,87,138,143,238],"theoretical":[16],"energy":[17],"benefits":[18],"of":[19,52,79,89,129,240],"SNNs":[20],"are":[21,126,254],"often":[22],"decoupled":[23],"from":[24,177,234],"real-world":[25],"hardware":[26,80,130,232],"performance":[27,245],"due":[28],"to":[29,82,152,179,184,223],"opaque":[31],"relationship":[32],"between":[33],"training-time":[34],"choices":[35],"and":[36,47,58,99,107,117,202,216,250],"inference-time":[37],"sparsity.":[38],"While":[39],"prior":[40],"work":[41],"has":[42],"focused":[43],"on":[44,104,141,157,194],"weight":[45],"pruning":[46],"model":[48,60,168],"compression,":[49],"role":[51],"training":[53,235],"hyperparameters\u2014specifically":[54],"surrogate":[55,90],"gradient":[56,91],"functions":[57,92],"neuron":[59,100,167],"configurations\u2014in":[61],"shaping":[62],"hardware-level":[63],"activation":[64],"sparsity":[65],"remains":[66],"underexplored.":[67],"This":[68],"paper":[69],"presents":[70],"a":[71,185,195,228],"comprehensive":[72],"workload":[73],"characterization":[74,204],"study":[75],"quantifying":[76],"sensitivity":[78],"latency":[81,149,188,217],"SNN":[83,199,244],"hyperparameters.":[84],"We":[85,190],"decouple":[86],"impact":[88],"(e.g.,":[93],"Fast":[94,135],"Sigmoid,":[95],"Spike":[96,144],"Rate":[97,145],"Escape)":[98],"models":[101],"(LIF,":[102],"Lapicque)":[103],"classification":[105],"accuracy":[106,124,140,161,212],"efficiency":[109],"across":[110],"three":[111],"event-based":[112],"vision":[113],"datasets:":[114],"DVS128-Gesture,":[115],"N-MNIST,":[116],"DVS-CIFAR10.":[118],"Our":[119],"analysis":[120,193],"reveals":[121],"that":[122,166,206],"standard":[123],"metrics":[125],"poor":[127],"predictors":[128],"efficiency.":[131],"For":[132],"instance,":[133],"while":[134],"Sigmoid":[136],"achieves":[137],"highest":[139],"DVS-CIFAR10,":[142],"Escape":[146],"reduces":[147],"by":[150,213,218],"up":[151,183],"$\\mathbf{1":[153],"2.":[154],"2":[155],"\\%}$":[156],"DVS128-Gesture":[158],"with":[159],"minimal":[160],"trade-offs.":[162],"Furthermore,":[163],"we":[164],"demonstrate":[165],"selection":[169,209],"is":[170],"as":[171,173],"critical":[172],"parameter":[174],"tuning;":[175],"transitioning":[176],"LIF":[178],"Lapicque":[180],"neurons":[181],"yields":[182],"$28":[186],"\\%$":[187,215],"reduction.":[189],"validate":[191],"our":[192,203],"custom":[196],"cycle-accurate":[197],"FPGA-based":[198],"instrumentation":[200],"platform,":[201],"demonstrates":[205],"sparsity-aware":[207],"hyperparameter":[208],"can":[210],"improve":[211],"$9.1":[214],"over":[219],"$2":[220],"\\times$":[221],"compared":[222],"baselines.":[224],"These":[225],"findings":[226],"establish":[227],"methodology":[229],"predicting":[231],"behavior":[233],"parameters,":[236],"motivating":[237],"inclusion":[239],"sparsity-sensitivity":[241],"in":[242],"future":[243],"analysis.":[246],"The":[247],"RTL":[248],"code":[249],"other":[251],"reproducibility":[252],"artifacts":[253],"available":[255],"at":[256],"https://zenodo.org/records/18893738.":[257]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-05-27T00:00:00"}