{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002957406,0.0001437985,0.0001426615,0.0001223814,0.00008693075,0.0001822712,0.0003414708,0.00006284745,0.0001405351],"category_scores_gemma":[0.00004588226,0.0001480232,0.00009238091,0.0001868529,0.00001088963,0.0005321102,0.00005362516,0.000151565,0.0001248093],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004217242,"about_ca_system_score_gemma":0.0000211962,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005633104,"about_ca_topic_score_gemma":0.000002165954,"domain_scores_codex":[0.9987263,0.0001432055,0.0002342659,0.0004643026,0.0001792709,0.0002526557],"domain_scores_gemma":[0.9990589,0.0003000421,0.0001631403,0.0003185016,0.00006589138,0.00009351464],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002203859,0.00002174772,0.003613602,0.00002193021,0.0000272008,9.080538e-7,0.0001055379,0.3145458,0.0006089715,0.0001240469,0.005816845,0.6750914],"study_design_scores_gemma":[0.000719541,0.0000509312,0.001888637,0.00001535873,0.00001243665,0.00001540355,0.000007625936,0.9956718,0.00004826938,0.00009463955,0.001274659,0.0002006625],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00484016,0.00001553714,0.9843998,0.009269175,0.0007878713,0.0004078523,0.0000176864,0.0001823161,0.00007958968],"genre_scores_gemma":[0.131405,0.000005344592,0.8529603,0.01407484,0.0003204732,0.0000803373,0.001030579,0.00002416602,0.000098868],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6811261,"threshold_uncertainty_score":0.6036212,"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."}}