{"id":"W3083082685","doi":"10.1109/tvcg.2020.3030380","title":"HyperTendril: Visual Analytics for User-Driven Hyperparameter Optimization of Deep Neural Networks","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Visualization and Computer Graphics","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Korea Electric Power Corporation; National Research Foundation of Korea","keywords":"Hyperparameter; Computer science; Hyperparameter optimization; Visual analytics; Machine learning; Task (project management); Artificial intelligence; Analytics; Set (abstract data type); Artificial neural network; Visualization; Data mining; Support vector machine","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":[0.004312051,0.003025042,0.001061284,0.002126392,0.0004809143,0.002706067,0.004064899,0.001435658,0.01547681],"category_scores_gemma":[0.01976939,0.001092021,0.001158146,0.0006591989,0.0007380788,0.00286909,0.004033434,0.002441456,0.004021059],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008888282,"about_ca_system_score_gemma":0.001128689,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002656854,"about_ca_topic_score_gemma":0.005814431,"domain_scores_codex":[0.9984168,0.000584137,0.0001350227,0.0003307076,0.0004261932,0.0001071365],"domain_scores_gemma":[0.9907038,0.006824547,0.0004140161,0.001021285,0.0007378725,0.0002984035],"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":[0.003183078,0.0009986266,0.01056699,0.002843622,0.0005458989,0.001089585,0.003371967,0.1341493,0.04529471,0.01898241,0.1310734,0.6479005],"study_design_scores_gemma":[0.0003870571,0.0001835412,0.001708193,0.0002208927,0.00004474703,0.0001565849,0.0002010421,0.9277207,0.02276094,0.0228647,0.02360243,0.0001491808],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01568889,0.0004626828,0.7531261,0.0004547036,0.0001051969,0.0003391726,0.002488635,0.2245085,0.002826152],"genre_scores_gemma":[0.2292636,0.0005248851,0.7370127,0.0009873711,0.00007460218,0.001532264,0.004408726,0.0221333,0.004062415],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01547681,"threshold_uncertainty_score":0.05177504,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02878727736384121,"score_gpt":0.2790546234670804,"score_spread":0.2502673461032391,"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."}}