{"id":"W2892242726","doi":"10.48550/arxiv.1810.11393","title":"Dendritic cortical microcircuits approximate the backpropagation algorithm","year":2018,"lang":"en","type":"preprint","venue":"Bern Open Repository and Information System (University of Bern)","topic":"Neural dynamics and brain function","field":"Neuroscience","cited_by":68,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"Horizon 2020 Framework Programme; Natural Sciences and Engineering Research Council of Canada; European Commission; Canada Research Chairs; Canadian Institute for Advanced Research; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Backpropagation; Computer science; Neuroscience; Artificial neural network; Artificial intelligence; Deep learning; Biological neural network; Machine learning; 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":[0.0002263088,0.0004524955,0.0004405294,0.0003277086,0.0002189459,0.0006459783,0.001019475,0.0009094202,0.001886506],"category_scores_gemma":[0.001621526,0.0002845242,0.000289615,0.0003355044,0.0004929886,0.0008953519,0.0004966572,0.0006432309,0.0005128356],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001059395,"about_ca_system_score_gemma":0.0008781914,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01085591,"about_ca_topic_score_gemma":0.00783474,"domain_scores_codex":[0.9999113,0.00001575416,0.000004551331,0.00002229321,0.00003073967,0.00001538939],"domain_scores_gemma":[0.9997336,0.0001033278,0.00004091324,0.00003227337,0.00007081691,0.00001909918],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002617171,0.00001018005,0.0005486156,0.00003151229,0.0000163226,0.00004187408,0.00001852125,0.9491048,0.002709132,0.02884909,0.0009923158,0.01765143],"study_design_scores_gemma":[0.000001817933,0.000002034677,0.00006484063,0.000001331102,0.00000139309,0.000008357678,0.000001215039,0.9938217,0.0002109703,0.005652616,0.0002322205,0.000001354487],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05408462,0.0005057359,0.9375722,0.0007421751,0.00005561594,0.00002389547,0.0001374832,0.0008947199,0.005983575],"genre_scores_gemma":[0.8891619,0.0006987772,0.09895932,0.0001186588,0.00004641214,0.00006672025,0.000135271,0.0001234015,0.01068938],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01085591,"threshold_uncertainty_score":0.02158546,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02059577636203979,"score_gpt":0.2106922147391168,"score_spread":0.190096438377077,"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."}}