{"id":"W3090228367","doi":"","title":"Batch norm with entropic regularization turns deterministic autoencoders into generative models","year":2020,"lang":"en","type":"article","venue":"Uncertainty in Artificial Intelligence","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Autoencoder; Computer science; Generative model; Regularization (linguistics); Generative grammar; Encoder; Algorithm; Artificial neural network; Artificial intelligence; Encoding (memory); Matrix norm; Source code; Normalization (sociology); Theoretical computer science; Eigenvalues and eigenvectors","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":[0.001685646,0.001042328,0.0006586974,0.0004770183,0.0003121414,0.0009561722,0.001099365,0.001101708,0.002160199],"category_scores_gemma":[0.005250606,0.0006791723,0.000854335,0.0004092769,0.002198111,0.001735711,0.001778811,0.002595612,0.0004676661],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001271451,"about_ca_system_score_gemma":0.0008420793,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002581399,"about_ca_topic_score_gemma":0.002848032,"domain_scores_codex":[0.9992996,0.0002953725,0.00002529453,0.0001587998,0.0001717825,0.00004914305],"domain_scores_gemma":[0.9984018,0.00116843,0.0001046003,0.0001723942,0.00009851356,0.00005418161],"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":[0.00003728399,0.00002549941,0.0002442059,0.00004698731,0.00004207861,0.00007046235,0.00008121165,0.6238079,0.003995813,0.3477976,0.001364858,0.02248615],"study_design_scores_gemma":[0.00000259188,0.00001021932,0.00004102222,0.000007021595,0.000004025278,0.00001487908,0.000003502716,0.92858,0.0009333208,0.06968754,0.0007095595,0.000006386903],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004153128,0.0001158534,0.9931405,0.0001913317,0.00002530901,0.0000110215,0.00002749248,0.0001380307,0.002197322],"genre_scores_gemma":[0.6541507,0.0008517821,0.3280889,0.0005574668,0.0002154149,0.0001782857,0.0002485776,0.0005019425,0.01520693],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002581399,"threshold_uncertainty_score":0.00922513,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04116235678626784,"score_gpt":0.2522136720768242,"score_spread":0.2110513152905563,"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."}}