{"id":"W3033960544","doi":"10.1109/tnnls.2021.3069970","title":"EDropout: Energy-Based Dropout and Pruning of Deep Neural Networks","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks and Learning Systems","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":53,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Fujitsu","keywords":"Pruning; Artificial neural network; Dropout (neural networks); Population; Computer science; Backpropagation; Probabilistic logic; Artificial intelligence; Algorithm; Machine learning","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":[0.002336417,0.00154467,0.001435019,0.0009395051,0.0006736401,0.001096953,0.003645298,0.002133713,0.002950776],"category_scores_gemma":[0.005071919,0.0007064191,0.001182353,0.0008299505,0.0008815806,0.002171056,0.002080167,0.002336519,0.0006896319],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001425274,"about_ca_system_score_gemma":0.001429867,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004627794,"about_ca_topic_score_gemma":0.008921813,"domain_scores_codex":[0.9989632,0.0002088029,0.00009194352,0.0001889284,0.0004137804,0.0001332311],"domain_scores_gemma":[0.9986526,0.000599784,0.0001521313,0.0002209735,0.0003057214,0.0000688327],"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":[0.0003984299,0.0003109392,0.001961667,0.0002623082,0.000223638,0.0003282633,0.0001372805,0.66127,0.009867694,0.01544923,0.0101007,0.2996899],"study_design_scores_gemma":[0.000027248,0.00005799871,0.0002276613,0.00002140865,0.00001761251,0.00004388812,0.000007140992,0.9878975,0.005697698,0.00438654,0.001605544,0.000009854427],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02538473,0.0008557314,0.966735,0.0002847718,0.0001131334,0.00015411,0.0002890608,0.003895845,0.002287632],"genre_scores_gemma":[0.4128031,0.0006593392,0.5718191,0.0007425581,0.0001156831,0.0006639562,0.001891141,0.00109559,0.01020952],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004627794,"threshold_uncertainty_score":0.01235628,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009987216775506999,"score_gpt":0.2260192393803364,"score_spread":0.2160320226048293,"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."}}