{"id":"W2990189480","doi":"10.1109/mlsp49062.2020.9231761","title":"Regularizing Neural Networks by Stochastically Training Layer Ensembles","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Regularization (linguistics); Artificial neural network; Computer science; Stochastic neural network; Network topology; Ensemble learning; Dropout (neural networks); Artificial intelligence; Algorithm; Machine learning; Mathematics; Time delay neural network","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":[0.0001460809,0.0004640851,0.0004924195,0.0000592008,0.0002160721,0.0003939703,0.00230552,0.0003099323,0.00001672381],"category_scores_gemma":[0.00006389756,0.0004591057,0.0001800095,0.0004098998,0.00008366755,0.0002499862,0.003140523,0.00134529,0.00002348287],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005749059,"about_ca_system_score_gemma":0.00007678199,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008455149,"about_ca_topic_score_gemma":0.000004006692,"domain_scores_codex":[0.9969382,0.00008991075,0.0005241314,0.00141376,0.0003842428,0.000649784],"domain_scores_gemma":[0.9976982,0.0003531408,0.0002521765,0.001257944,0.0000911637,0.000347369],"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":[0.00001318738,0.0000505993,0.00001394725,0.00003818232,0.00007737694,0.0000411891,0.0008007544,0.6855913,0.003708541,0.1406487,0.03237389,0.1366423],"study_design_scores_gemma":[0.0001152602,0.00003142952,0.00002517019,0.0000328453,0.00001513326,0.00001545714,0.00001952665,0.9694483,0.0001733205,0.02748084,0.002166744,0.0004759555],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.000184508,0.0003820682,0.9823017,0.01290055,0.0005281796,0.0005271193,0.000008068982,0.001150835,0.002016994],"genre_scores_gemma":[0.6948794,0.00003034813,0.3005478,0.0035023,0.0005081873,0.0001674763,0.00005877093,0.0000537734,0.0002519578],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6946949,"threshold_uncertainty_score":0.9997861,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05980751951435766,"score_gpt":0.2871169137032405,"score_spread":0.2273093941888829,"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."}}