{"id":"W3094058074","doi":"10.1016/j.neucom.2020.07.127","title":"A compensation-based optimization strategy for top dense layer training","year":2020,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Machine Learning and ELM","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Lakehead University; University of Windsor","funders":"","keywords":"Training (meteorology); Computer science; Layer (electronics); Compensation (psychology); Artificial intelligence; Machine learning; Mathematical optimization; Mathematics; Materials science; Psychology; Nanotechnology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007451192,0.001165768,0.000877146,0.0005558684,0.0005729456,0.0007699978,0.00164102,0.001577875,0.007362911],"category_scores_gemma":[0.002072402,0.0005527352,0.0005078485,0.0007346992,0.0006436859,0.001023523,0.001419223,0.001591975,0.001543163],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005435352,"about_ca_system_score_gemma":0.00171315,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007257413,"about_ca_topic_score_gemma":0.01237439,"domain_scores_codex":[0.9996914,0.00005804825,0.00002177445,0.00005962464,0.0001129938,0.0000562389],"domain_scores_gemma":[0.999631,0.0001063061,0.0000249207,0.00005932764,0.0001439667,0.00003447957],"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":[0.0002569849,0.0001692669,0.0004663012,0.0001840149,0.00009172152,0.0001242891,0.0001165975,0.5000997,0.03610977,0.03117589,0.01238523,0.4188202],"study_design_scores_gemma":[0.000008167788,0.00002099994,0.00006319476,0.000007084741,0.00000670195,0.00002155738,0.0000068698,0.9938939,0.00265724,0.002462348,0.0008456863,0.000006155788],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003128547,0.0001011489,0.9941646,0.00009859199,0.00005777707,0.00003476081,0.00002832909,0.0004641949,0.001922064],"genre_scores_gemma":[0.2458754,0.0001748979,0.742803,0.0003785768,0.00009305938,0.0002327331,0.0002808504,0.0003741538,0.009787327],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007362911,"threshold_uncertainty_score":0.02463138,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07604324183366765,"score_gpt":0.2902808595574789,"score_spread":0.2142376177238113,"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."}}