{"id":"W4390993409","doi":"10.1109/biocas58349.2023.10388882","title":"STDG: Fast and Lightweight SNN Training Technique Using Spike Temporal Locality","year":2023,"lang":"en","type":"article","venue":"","topic":"Advanced Memory and Neural Computing","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University; University of Toronto","funders":"","keywords":"Spiking neural network; Spike (software development); MNIST database; Computer science; Asynchronous communication; Neuromorphic engineering; Locality; Efficient energy use; Artificial intelligence; Artificial neural network; Energy (signal processing); Face (sociological concept); Machine learning; Pattern recognition (psychology); Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006900277,0.0007250866,0.0006010114,0.0005330106,0.0003293502,0.0003638687,0.001609437,0.0006229465,0.002195528],"category_scores_gemma":[0.001885666,0.0003483779,0.0004067192,0.0005492629,0.0003683617,0.0008780575,0.001048167,0.001091599,0.0007128216],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004324518,"about_ca_system_score_gemma":0.001196213,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0037759,"about_ca_topic_score_gemma":0.0103725,"domain_scores_codex":[0.9997755,0.00003688337,0.0000159645,0.00005131733,0.00009398363,0.00002637826],"domain_scores_gemma":[0.9996021,0.000109129,0.00004384,0.0000766159,0.000134379,0.00003390159],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003035871,0.0001485784,0.00403835,0.0001503777,0.0001287144,0.0001645666,0.0001309083,0.2386284,0.03068379,0.006415983,0.009324403,0.7098823],"study_design_scores_gemma":[0.00002146025,0.00005854561,0.0004411105,0.00000690158,0.00001017567,0.00006821223,0.00001310296,0.9882322,0.007297166,0.002354485,0.001486297,0.00001035165],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04219219,0.0003977781,0.9502249,0.0002706476,0.0001333948,0.0001091632,0.0002117666,0.00479057,0.001669617],"genre_scores_gemma":[0.5359151,0.0002825615,0.4574666,0.0003349942,0.00005656214,0.0002429262,0.0008381958,0.0004454204,0.004417569],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0037759,"threshold_uncertainty_score":0.007507861,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05449313237837822,"score_gpt":0.2753339703892876,"score_spread":0.2208408380109094,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}