{"id":"W2775632911","doi":"10.15353/vsnl.v3i1.175","title":"Estimating Optimal Depth of VGG Net with Tree-Structured Parzen Estimators","year":2017,"lang":"en","type":"article","venue":"Journal of Computational Vision and Imaging Systems","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Sunnybrook Hospital; University of Toronto","funders":"","keywords":"Estimator; Computer science; Computation; Convolutional neural network; Grid; Tree (set theory); Architecture; Artificial intelligence; Pattern recognition (psychology); Algorithm; Mathematics; Statistics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002787981,0.0001346211,0.0002971159,0.0001213884,0.0003303525,0.0004021195,0.0005874585,0.00002116974,7.427074e-7],"category_scores_gemma":[0.00006236674,0.00009638636,0.00004987349,0.0001011224,0.0001270502,0.001087963,0.0001176455,0.0001429782,8.395757e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002257717,"about_ca_system_score_gemma":0.00008083213,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008703498,"about_ca_topic_score_gemma":8.542945e-7,"domain_scores_codex":[0.998677,0.00004764534,0.0005274829,0.0001588776,0.0004496937,0.0001393387],"domain_scores_gemma":[0.997619,0.0002010952,0.001404231,0.0002727096,0.0003864691,0.0001164891],"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":[0.0000289775,0.00003070441,0.01094285,0.00004149726,0.00003378413,0.00002332963,0.0002387906,0.9298118,0.0002821144,0.006963484,0.0005925478,0.05101008],"study_design_scores_gemma":[0.0005972279,0.00009891709,0.05644526,0.0002368762,0.00001193229,0.0008490718,0.00003192776,0.9386606,0.00005270503,0.002747745,0.0001639727,0.0001037639],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1055616,0.0002304905,0.8930001,0.0006746358,0.0002953346,0.0001047769,0.000001694475,0.00001837948,0.0001130024],"genre_scores_gemma":[0.644113,0.000002037928,0.3557628,0.00002699401,0.00007937169,0.000001248844,8.862474e-7,0.000006496779,0.000007152617],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5385514,"threshold_uncertainty_score":0.3930522,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01208679398853062,"score_gpt":0.2977692761548934,"score_spread":0.2856824821663628,"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."}}