{"id":"W4386617144","doi":"10.22541/au.169446658.81099759/v1","title":"STDG: Fast and Lightweight SNN Training Technique Using Spike Temporal Locality","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Advanced Memory and Neural Computing","field":"Engineering","cited_by":0,"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 neural network; Artificial intelligence; Energy (signal processing); Differentiable function; Pattern recognition (psychology); Machine learning; Algorithm; 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":[0.0007373681,0.0007469584,0.000616807,0.0005439399,0.0003301628,0.000391331,0.001694162,0.000666005,0.002257756],"category_scores_gemma":[0.002105805,0.0003688105,0.0004137119,0.0005797559,0.0003965994,0.0009319715,0.001134542,0.001148267,0.000775789],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004423844,"about_ca_system_score_gemma":0.001198039,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003600799,"about_ca_topic_score_gemma":0.009719766,"domain_scores_codex":[0.9997571,0.00004259215,0.00001718371,0.00005484436,0.0001010747,0.00002722761],"domain_scores_gemma":[0.9995554,0.0001251134,0.00004722943,0.00009415967,0.0001414814,0.00003670844],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003128783,0.0001463523,0.003731797,0.0001549733,0.0001316461,0.0001601014,0.0001343255,0.2455158,0.03036217,0.007229126,0.009944116,0.7021767],"study_design_scores_gemma":[0.00002180976,0.00005441419,0.0003892292,0.000006794016,0.000009622728,0.00006391053,0.00001233231,0.9879023,0.007304984,0.002752042,0.001472669,0.000009945954],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03745092,0.0003709742,0.9551745,0.0002668429,0.0001248826,0.0001006346,0.0002098613,0.004798947,0.001502469],"genre_scores_gemma":[0.5042878,0.0002772908,0.4889834,0.0003287077,0.00006036224,0.0002482434,0.0008683695,0.0005064949,0.004439351],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003600799,"threshold_uncertainty_score":0.007552981,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1017465095439487,"score_gpt":0.2991815195837815,"score_spread":0.1974350100398328,"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."}}