{"id":"W4388052734","doi":"10.1109/jetcas.2023.3328926","title":"Spike Timing Dependent Gradient for Direct Training of Fast and Efficient Binarized Spiking Neural Networks","year":2023,"lang":"en","type":"article","venue":"IEEE Journal on Emerging and Selected Topics in Circuits and Systems","topic":"Advanced Memory and Neural Computing","field":"Engineering","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"MNIST database; Computer science; Spiking neural network; Neuromorphic engineering; Speedup; Backpropagation; Spike (software development); Artificial neural network; Artificial intelligence; Efficient energy use; Pattern recognition (psychology); Parallel computing","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.0004615295,0.0001590095,0.0003437729,0.0002344927,0.0002106316,0.00006350753,0.00005099653,0.00006480848,2.39337e-7],"category_scores_gemma":[0.00004941495,0.0001392361,0.0000331909,0.0002822934,0.0000178263,0.00004920958,0.00001151656,0.0003124656,3.893416e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003349287,"about_ca_system_score_gemma":0.000006546647,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004293882,"about_ca_topic_score_gemma":0.000004271413,"domain_scores_codex":[0.9989007,0.00004991999,0.0004054103,0.0001796618,0.0001270762,0.0003371917],"domain_scores_gemma":[0.9995076,0.000196087,0.00009947694,0.00005755524,0.00004928414,0.00008996898],"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":[0.00001159342,0.000007398583,0.0005273508,0.0001827137,0.00002717016,0.00003097882,0.002070306,0.9387085,0.007208326,0.0001059929,0.000007916554,0.05111177],"study_design_scores_gemma":[0.0006949872,0.0001269026,0.001177807,0.0004390483,0.00001549451,0.0001613035,0.0005131737,0.9961601,0.0003882421,0.00002480231,0.0001348529,0.0001632426],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9899174,0.001152748,0.007252329,0.00002395058,0.001334924,0.0001738335,0.000002160776,0.0000685601,0.00007411579],"genre_scores_gemma":[0.9992356,0.0003292752,0.00002456373,0.000009011679,0.0003380216,0.000005973195,0.000001566457,0.00002115335,0.00003481321],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05745165,"threshold_uncertainty_score":0.5677884,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04430999213860597,"score_gpt":0.2674305585845955,"score_spread":0.2231205664459895,"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."}}