{"id":"W4285252396","doi":"10.1109/tetci.2022.3174905","title":"Modulating STDP With Back-Propagated Error Signals to Train SNNs for Audio Classification","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Emerging Topics in Computational Intelligence","topic":"Advanced Memory and Neural Computing","field":"Engineering","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Spiking neural network; Artificial intelligence; Backpropagation; Deep learning; Artificial neural network; Speech recognition; Learning rule; Machine learning; Pattern recognition (psychology)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006419595,0.0006109899,0.0004179155,0.0003695486,0.0002331096,0.0004655706,0.001028732,0.0006029179,0.0009149204],"category_scores_gemma":[0.002589499,0.0002231243,0.0004402781,0.0003171149,0.000334615,0.0007834802,0.0004705287,0.001165004,0.0003601191],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004858977,"about_ca_system_score_gemma":0.0006011162,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004552638,"about_ca_topic_score_gemma":0.006976826,"domain_scores_codex":[0.9998046,0.00002465102,0.00002071106,0.00005636953,0.00006800047,0.000025614],"domain_scores_gemma":[0.9992707,0.0003085035,0.00009259218,0.00008577525,0.0002173128,0.0000251892],"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":[0.0001653533,0.0001235964,0.00301306,0.00009439968,0.0000784252,0.0000900117,0.00006419823,0.6989467,0.02574844,0.002094605,0.001274438,0.2683069],"study_design_scores_gemma":[0.000002637393,0.00002169485,0.0001809212,0.000002955366,0.000004978876,0.000008739984,0.000003046308,0.99463,0.004593886,0.0003947163,0.0001534135,0.000002959191],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1895073,0.0006409349,0.8036148,0.000265789,0.0001775411,0.00009554743,0.0002335729,0.003115689,0.002348759],"genre_scores_gemma":[0.8391863,0.0002327565,0.1578706,0.000135685,0.00003190262,0.000101314,0.0004247856,0.00009417657,0.001922527],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004552638,"threshold_uncertainty_score":0.009052277,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07404502785326134,"score_gpt":0.3194630438817723,"score_spread":0.2454180160285109,"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."}}