{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002035405,0.0002945864,0.0003232212,0.0001133005,0.0001775994,0.0003030332,0.0008192108,0.00009638636,0.00004389306],"category_scores_gemma":[0.0001810995,0.0002521394,0.0000703008,0.0009952181,0.0001868369,0.0007413381,0.0001747249,0.000250925,0.00005192933],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001374784,"about_ca_system_score_gemma":0.0002012698,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003089765,"about_ca_topic_score_gemma":0.001023952,"domain_scores_codex":[0.9976653,0.0002021291,0.0005358087,0.0007710872,0.0003817734,0.0004438931],"domain_scores_gemma":[0.9988546,0.000165416,0.0001587609,0.0004105969,0.0002094819,0.0002010938],"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":[0.00005225503,0.00005043253,0.00002874473,0.0000123005,0.00001557449,0.00003661852,0.009294292,0.8844852,0.001578351,0.07177978,0.00003846842,0.03262793],"study_design_scores_gemma":[0.00005584618,0.0002466824,0.0000124505,0.00003174781,0.000009574313,0.000002649675,0.0005237999,0.9081054,0.01087187,0.07970461,0.000140809,0.0002945843],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002039416,0.00006065136,0.9915144,0.005179476,0.0002253792,0.0003635371,0.00000321622,0.0001070771,0.0005068138],"genre_scores_gemma":[0.9072923,0.00003114641,0.09125718,0.001120872,0.0002033944,0.00003688584,0.000009506556,0.00001597023,0.00003275504],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9052529,"threshold_uncertainty_score":0.9999931,"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."}}