{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002458579,0.001294559,0.001140796,0.0004638473,0.0003998838,0.0007954232,0.001528875,0.00161672,0.001105985],"category_scores_gemma":[0.007385878,0.0007527235,0.0008748857,0.0005035304,0.0008075035,0.002538681,0.001948131,0.002861463,0.0005375537],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005579519,"about_ca_system_score_gemma":0.0006217234,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001520906,"about_ca_topic_score_gemma":0.00323879,"domain_scores_codex":[0.9990516,0.0004073305,0.00005512584,0.000171989,0.0002272531,0.0000866679],"domain_scores_gemma":[0.9976835,0.001045132,0.0002431529,0.0005915677,0.0003462193,0.00009043048],"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":[0.00007160405,0.00005622759,0.0007018399,0.00003321879,0.00007556457,0.00004195898,0.00003494932,0.9476069,0.006654247,0.008032094,0.0008538495,0.03583741],"study_design_scores_gemma":[0.0000018835,0.00001283123,0.00004175013,0.000001676562,0.000003140803,0.000005581046,0.000001251521,0.9964966,0.0009487449,0.002399098,0.0000851489,0.000002299334],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0488258,0.0001796689,0.9487874,0.0002337737,0.00004696855,0.00002214674,0.00005106787,0.0008227946,0.001030249],"genre_scores_gemma":[0.7073354,0.0003362057,0.2883324,0.0002796862,0.0001323567,0.000134507,0.0004215143,0.0003529511,0.002675062],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002458579,"threshold_uncertainty_score":0.01300234,"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."}}