{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00150523,0.00147698,0.001312411,0.001089351,0.0005475234,0.00136007,0.001891662,0.001832809,0.006562875],"category_scores_gemma":[0.004511326,0.0007606112,0.001014947,0.0009027597,0.0007707503,0.001364705,0.001924529,0.001995136,0.001726613],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001044984,"about_ca_system_score_gemma":0.001430009,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003731475,"about_ca_topic_score_gemma":0.007240742,"domain_scores_codex":[0.9994792,0.0002391097,0.00002662126,0.00009041966,0.0001250145,0.00003971575],"domain_scores_gemma":[0.9992602,0.0004370034,0.00005489506,0.0001123044,0.0001003437,0.00003516146],"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":[0.0002755825,0.0001295017,0.001345847,0.0003290684,0.0001917335,0.0001095663,0.0001165485,0.7564989,0.002845618,0.01905069,0.01932491,0.199782],"study_design_scores_gemma":[0.00004337111,0.00002456155,0.00008589494,0.00002125485,0.00000622577,0.00001930497,0.000009725966,0.9900885,0.0006561638,0.006681908,0.002355084,0.000007992156],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0150612,0.001337483,0.9694021,0.0002951738,0.0001578278,0.00019285,0.00038034,0.006701155,0.006471894],"genre_scores_gemma":[0.218021,0.0004476885,0.7725736,0.0005056434,0.0001013755,0.0008054259,0.0010347,0.002212878,0.004297566],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006562875,"threshold_uncertainty_score":0.02195507,"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."}}