{"id":"W3205784920","doi":"10.1609/aaai.v36i8.20874","title":"Hindsight Network Credit Assignment: Efficient Credit Assignment in Networks of Discrete Stochastic Units","year":2022,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates","keywords":"Backpropagation; Hindsight bias; Computer science; Estimator; Artificial neural network; Function (biology); Artificial intelligence; Variance (accounting); Mathematical optimization; Mathematics; Economics; Statistics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001575433,0.0002960935,0.0004146603,0.000227413,0.0004277779,0.0001692089,0.002433961,0.00007985016,0.0002369469],"category_scores_gemma":[0.0003569362,0.0002532641,0.0001188695,0.002076805,0.0002568758,0.0002218883,0.001125457,0.0007596833,0.00001292188],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001937521,"about_ca_system_score_gemma":0.0001962219,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003461782,"about_ca_topic_score_gemma":0.000005986245,"domain_scores_codex":[0.9964541,0.0001165459,0.000959358,0.0006342812,0.001227728,0.0006080463],"domain_scores_gemma":[0.9979515,0.0002932318,0.0008535601,0.0003824605,0.000384312,0.0001349181],"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":[0.00009621997,0.0001692292,0.0001229152,0.0000139288,0.00001554529,0.000001363617,0.001987777,0.6218389,0.001643385,0.3637965,0.0001951057,0.01011917],"study_design_scores_gemma":[0.0001005023,0.0004368169,0.0004003741,0.0002222916,0.0000154017,0.000004403885,0.001727038,0.9719863,0.005386455,0.01915836,0.0002623988,0.000299652],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03676793,0.0001245369,0.9507189,0.002071342,0.00204086,0.001036141,0.00001218552,0.0001096849,0.0071184],"genre_scores_gemma":[0.9982823,0.00001037452,0.001056763,0.0001702415,0.0001227728,0.00009719958,0.000002314743,0.00001934274,0.0002386857],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9615144,"threshold_uncertainty_score":0.999992,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05522808581807579,"score_gpt":0.2657905339065713,"score_spread":0.2105624480884955,"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."}}