{"id":"W2914110112","doi":"10.1016/j.patrec.2019.02.009","title":"A new hyperparameters optimization method for convolutional neural networks","year":2019,"lang":"en","type":"article","venue":"Pattern Recognition Letters","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":105,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"National Key Research and Development Program of China; Canadian Institute for Advanced Research","keywords":"Hyperparameter; Hyperparameter optimization; Bayesian optimization; Computer science; Convolutional neural network; Gaussian process; Artificial intelligence; Artificial neural network; Machine learning; Gaussian; Algorithm; Support vector machine","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001523832,0.001714641,0.001236345,0.0008549592,0.0005121019,0.001172182,0.001967412,0.002065552,0.004370734],"category_scores_gemma":[0.003717768,0.001184529,0.001180583,0.0008956942,0.0006439884,0.001708525,0.001530496,0.00285229,0.001921864],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001041756,"about_ca_system_score_gemma":0.001428242,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005933094,"about_ca_topic_score_gemma":0.008907994,"domain_scores_codex":[0.9993194,0.0002303647,0.00004975557,0.0001492417,0.000197129,0.00005396489],"domain_scores_gemma":[0.9992958,0.0003203814,0.00005399558,0.00008690646,0.000204564,0.00003836181],"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":[0.0001714822,0.00009601392,0.0005326255,0.0001539626,0.0002250702,0.00008263619,0.00007843216,0.5779356,0.01314343,0.01753833,0.008992095,0.3810503],"study_design_scores_gemma":[0.00001701384,0.00001426501,0.00007055175,0.00001495021,0.00001681004,0.00001904219,0.000003984036,0.9918481,0.00165863,0.004406101,0.001920784,0.000009656952],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001492423,0.00022496,0.9968946,0.0000800259,0.00005191418,0.00002422687,0.00003395731,0.0005212982,0.0006764996],"genre_scores_gemma":[0.06920583,0.0003957326,0.9193346,0.000289888,0.0001736321,0.0003451779,0.0003512325,0.001167116,0.008736875],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005933094,"threshold_uncertainty_score":0.0146215,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02314881426054435,"score_gpt":0.2654592914709404,"score_spread":0.2423104772103961,"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."}}