{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002556442,0.00182953,0.001394214,0.0009345795,0.000506592,0.0009280253,0.001310872,0.001213351,0.002020431],"category_scores_gemma":[0.005142621,0.001101675,0.001095089,0.0008682552,0.001272022,0.001096205,0.001250393,0.001177457,0.0002731622],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00198415,"about_ca_system_score_gemma":0.002129815,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01019774,"about_ca_topic_score_gemma":0.01117944,"domain_scores_codex":[0.9990643,0.0003773367,0.00003739954,0.0001452269,0.000247077,0.0001286068],"domain_scores_gemma":[0.99734,0.001853465,0.0002449632,0.0001264563,0.0003386623,0.00009649067],"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":[0.000014978,0.000006632749,0.0001253122,0.00001140872,0.000009736854,0.000005965636,0.000004093546,0.995494,0.0001332321,0.0008524282,0.00009074064,0.003251443],"study_design_scores_gemma":[0.000002680844,0.000006790228,0.00002251517,0.00000159927,0.000001392351,0.000001301846,9.719278e-7,0.9991177,0.00006912828,0.0007316182,0.00004331713,9.837692e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06441301,0.0006003529,0.9289439,0.0003415124,0.00005677355,0.0001081227,0.0001168504,0.0005380605,0.004881468],"genre_scores_gemma":[0.8152708,0.0002604597,0.1800309,0.0001965384,0.0000424479,0.000303676,0.0002399122,0.0001932896,0.003461946],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01019774,"threshold_uncertainty_score":0.02027673,"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."}}