{"id":"W3173940976","doi":"","title":"HyperNOMAD: Hyperparameter optimization of deep neural networks using mesh adaptive direct search","year":2019,"lang":"en","type":"article","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal; Group for Research in Decision Analysis","funders":"","keywords":"MNIST database; Hyperparameter; Computer science; Artificial intelligence; Artificial neural network; Machine learning; Flexibility (engineering); Process (computing); Deep learning; Categorical variable; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007082801,0.0002529053,0.0003553934,0.0003622472,0.0001423531,0.0001922219,0.0009518554,0.0002012221,0.00003095408],"category_scores_gemma":[0.00009910979,0.0002474934,0.0001290826,0.0008012847,0.00006018244,0.0007788014,0.0003826454,0.0004096639,0.000009465761],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001933493,"about_ca_system_score_gemma":0.0000822651,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002973884,"about_ca_topic_score_gemma":0.000110943,"domain_scores_codex":[0.9977479,0.0003334032,0.0004251568,0.0005772337,0.0003997959,0.0005164958],"domain_scores_gemma":[0.9979922,0.0002056168,0.0002655199,0.001196477,0.0001747176,0.0001654483],"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":[0.00004041329,0.00007662693,0.02477973,0.00001322384,0.00002332113,0.000004693884,0.0001340969,0.9372191,0.001502471,0.006740766,0.00002306958,0.02944251],"study_design_scores_gemma":[0.0002615273,0.000154302,0.01057971,0.0000202523,0.00001517944,0.00003969684,0.00003253671,0.9875573,0.0009693785,0.00006311444,0.00005450237,0.0002525234],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06686341,0.0003922599,0.9305897,0.0004253315,0.0001512045,0.0004763124,0.000007579426,0.0003705971,0.0007236486],"genre_scores_gemma":[0.6893057,0.00002563798,0.3101979,0.0002562994,0.00004310821,0.00002909014,0.00002361658,0.00002644359,0.00009225757],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6224422,"threshold_uncertainty_score":0.9999977,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01656619601874932,"score_gpt":0.2422570999454284,"score_spread":0.2256909039266791,"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."}}