{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003066727,0.000408684,0.0004803033,0.0001516868,0.0001222859,0.00007207304,0.0002012934,0.0003370117,0.00001913112],"category_scores_gemma":[0.00002444203,0.0004025825,0.00009830426,0.0001628396,0.00005673165,0.0001092692,0.0005472114,0.00101567,0.00000713727],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008924961,"about_ca_system_score_gemma":0.00003572654,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002996893,"about_ca_topic_score_gemma":0.00001631182,"domain_scores_codex":[0.9984593,0.00003715042,0.0004248029,0.0005182843,0.0001542162,0.000406241],"domain_scores_gemma":[0.9993254,0.0000795654,0.00007504567,0.0003593841,0.00002973627,0.000130858],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000025832,0.00003090213,0.001095194,0.003259257,0.0002044672,0.00052295,0.001730529,0.860809,0.09104691,0.0008081524,0.0003379275,0.04012889],"study_design_scores_gemma":[0.0004440624,0.00006458996,0.0005745902,0.001993163,0.00009987142,0.0002193498,0.0006707685,0.7637341,0.2119539,0.01583385,0.002043977,0.002367808],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2730283,0.0002022161,0.7211519,0.00003926981,0.0008807259,0.0005292115,0.00002083106,0.002540058,0.001607418],"genre_scores_gemma":[0.9568586,0.00003768925,0.04230783,0.00002770945,0.0003611529,0.0000289446,0.00002560217,0.0001126693,0.0002397963],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6838303,"threshold_uncertainty_score":0.9998426,"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."}}