{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001791912,0.0001183754,0.0001381668,0.00004645704,0.0002308846,0.0002069282,0.0003547536,0.00003630799,0.000008266175],"category_scores_gemma":[0.000167264,0.0001236767,0.00006180887,0.0002748269,0.000009762905,0.0001242667,0.00006227008,0.0001202198,0.000008655095],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009158328,"about_ca_system_score_gemma":0.00007666411,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006069758,"about_ca_topic_score_gemma":6.117495e-7,"domain_scores_codex":[0.9989387,0.00008167448,0.0002081037,0.0003767443,0.00014774,0.0002469778],"domain_scores_gemma":[0.9992561,0.0003036339,0.0001099765,0.0001537088,0.00007124139,0.0001053739],"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":[0.000005617456,0.00001004495,0.0001344745,0.00002076058,0.000002752922,0.000004011742,0.000735527,0.9419567,0.0001825458,0.001580524,0.0001256093,0.05524142],"study_design_scores_gemma":[0.0005138458,0.0001368352,0.0003892366,0.00001289462,0.000003615156,0.000003586062,0.00002634743,0.9969626,0.0001617424,0.0000539635,0.001609553,0.0001257613],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02470409,0.000008409248,0.9697142,0.0042011,0.0001216059,0.0001899312,7.027523e-7,0.0004003913,0.0006595887],"genre_scores_gemma":[0.8231829,1.613017e-7,0.1729969,0.003600807,0.0001862859,0.000006020536,0.000004701636,0.00001290809,0.000009316673],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7984788,"threshold_uncertainty_score":0.5043389,"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."}}