{"id":"W3091080409","doi":"10.1109/ijcnn48605.2020.9207659","title":"A Novel way of Training a Neural Network with Reinforcement learning and without Back Propagation","year":2020,"lang":"en","type":"article","venue":"","topic":"Optimization and Search Problems","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University; Royal Military College of Canada","funders":"","keywords":"Reinforcement learning; Computer science; Artificial neural network; Worry; Gradient descent; Backpropagation; Artificial intelligence; Learning automata; Core (optical fiber); Action (physics); Automaton","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0001334782,0.00006065119,0.00009407786,0.00001805464,0.00005666119,0.00006569921,0.0001072728,0.00001487037,0.00003348188],"category_scores_gemma":[0.0000169392,0.00004401854,0.00001011239,0.0002516835,0.0000275126,0.0002559646,0.00007968925,0.00008230754,0.000003101788],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004229014,"about_ca_system_score_gemma":0.00003196685,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006029331,"about_ca_topic_score_gemma":0.000002705965,"domain_scores_codex":[0.999381,0.00002332804,0.0001337117,0.0001590571,0.0001648331,0.0001380577],"domain_scores_gemma":[0.9997143,0.0000169652,0.0000662754,0.00006067295,0.00005924609,0.00008256095],"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":[0.00002301178,0.000007034868,0.001937299,0.00003241118,0.00001121774,4.885491e-7,0.005442907,0.9691833,0.001006742,0.01137111,0.00005049432,0.010934],"study_design_scores_gemma":[0.0004904735,0.0003621953,0.0001725801,0.00002033477,0.000001588782,0.000004100561,0.000108086,0.9982383,0.0001400027,0.00001053853,0.0003881462,0.00006370682],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002542416,0.000007010401,0.9903879,0.001436646,0.00001020274,0.0001892156,4.383885e-8,0.00005519393,0.005371327],"genre_scores_gemma":[0.7995622,0.000003654957,0.1996549,0.0003840824,0.00001799299,0.000004119208,0.000001326937,0.000003933069,0.0003677884],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7970198,"threshold_uncertainty_score":0.1795024,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04778871109854664,"score_gpt":0.2548645749179814,"score_spread":0.2070758638194348,"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."}}