{"id":"W2552737632","doi":"10.1038/ncomms13276","title":"Random synaptic feedback weights support error backpropagation for deep learning","year":2016,"lang":"en","type":"article","venue":"Nature Communications","topic":"Advanced Memory and Neural Computing","field":"Engineering","cited_by":851,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Vetenskapsrådet","keywords":"Backpropagation; Computer science; Mechanism (biology); Constraint (computer-aided design); Mistake; Artificial intelligence; Blame; Artificial neural network; Synaptic weight; Mathematics","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":[0.001361856,0.001083693,0.0007000917,0.0005784354,0.0004396549,0.001011599,0.002377681,0.00177298,0.00383907],"category_scores_gemma":[0.01250654,0.000451039,0.000582722,0.000624392,0.001222376,0.002198584,0.001479198,0.003021974,0.001463562],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000940696,"about_ca_system_score_gemma":0.001044473,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002150312,"about_ca_topic_score_gemma":0.002770466,"domain_scores_codex":[0.9991925,0.0001450224,0.00004540958,0.0001528182,0.0003943344,0.00006982295],"domain_scores_gemma":[0.9979094,0.0009620877,0.0001968613,0.0003440704,0.000494654,0.00009293715],"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":[0.0003601548,0.0001366661,0.0006231599,0.0002125277,0.00009914424,0.0002407091,0.00009731306,0.5660297,0.01442632,0.2564245,0.00801756,0.1533323],"study_design_scores_gemma":[0.00002252556,0.00002132315,0.00005304137,0.00001377227,0.000008509895,0.00002416707,0.000003029719,0.9306833,0.002511523,0.06499983,0.001648293,0.00001065546],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01488928,0.0004663814,0.975953,0.0008561297,0.00021745,0.00005111347,0.0001162923,0.001620514,0.005829746],"genre_scores_gemma":[0.5961227,0.0007883743,0.3900532,0.0005018963,0.0002595679,0.0002619807,0.0003023877,0.0005260028,0.01118391],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00383907,"threshold_uncertainty_score":0.01284301,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01933405323896934,"score_gpt":0.2786935998621625,"score_spread":0.2593595466231931,"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."}}