{"id":"W3035888673","doi":"10.23919/date48585.2020.9116535","title":"Probabilistic Sequential Multi-Objective Optimization of Convolutional Neural Networks","year":2020,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; MNIST database; Hyperparameter; Probabilistic logic; Convolutional neural network; Pareto principle; Multi-objective optimization; Speedup; Inference; Parameterized complexity; Artificial intelligence; Machine learning; Bayesian optimization; Mathematical optimization; Artificial neural network; Algorithm; Mathematics","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":[0.00009378235,0.0000643998,0.0000833697,0.00002356818,0.00005035822,0.00003738925,0.0002766481,0.00003380109,0.00004441776],"category_scores_gemma":[0.0001617034,0.00005764622,0.0000295786,0.0002402355,0.00004002868,0.0002466909,0.0001036184,0.00009638246,0.000006102792],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001538303,"about_ca_system_score_gemma":0.00003710592,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003154911,"about_ca_topic_score_gemma":0.000002895186,"domain_scores_codex":[0.9992874,0.00008614935,0.0001653791,0.0002367725,0.0001291368,0.00009511921],"domain_scores_gemma":[0.9995323,0.00004987249,0.00009336309,0.0001598287,0.0001053834,0.00005926795],"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":[0.000007298453,0.00002643028,0.0006765501,0.000007314533,0.00000525331,4.333927e-7,0.0001278764,0.9710653,0.0000545464,0.02598209,0.000184001,0.001862947],"study_design_scores_gemma":[0.0002270868,0.00005301798,0.00367901,0.000002029835,0.000003728187,0.000001865287,0.0000070623,0.9958297,0.00002493279,0.00005365081,0.00005584668,0.00006209339],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0004219268,0.00001934264,0.9972226,0.001474393,0.0001017558,0.0001143537,0.000003146761,0.0001815197,0.000460976],"genre_scores_gemma":[0.8846849,0.000001709126,0.1149135,0.0002482057,0.00005585622,0.000005388993,0.00005069327,0.000003357238,0.00003634255],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.884263,"threshold_uncertainty_score":0.2350744,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03493261542718523,"score_gpt":0.2640941623591727,"score_spread":0.2291615469319875,"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."}}