{"id":"W3006924020","doi":"10.48550/arxiv.2002.10631","title":"Batch norm with entropic regularization turns deterministic autoencoders into generative models","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Autoencoder; Regularization (linguistics); Generative grammar; Computer science; Generative model; Encoder; Algorithm; Matrix norm; Artificial neural network; Encoding (memory); Artificial intelligence; Normalization (sociology); Code (set theory); Source code; 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":[0.0001067211,0.0004862077,0.0004837841,0.0001699384,0.0002564771,0.0003140822,0.00148342,0.0002525259,0.00001963291],"category_scores_gemma":[0.00003149518,0.0004816747,0.0001761227,0.0006499684,0.0001721861,0.0007843302,0.001308247,0.0005012564,0.00002915584],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000270728,"about_ca_system_score_gemma":0.0004323891,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001539855,"about_ca_topic_score_gemma":0.0001713115,"domain_scores_codex":[0.9973826,0.0002701925,0.000252636,0.001527034,0.0001732564,0.0003943045],"domain_scores_gemma":[0.9980174,0.00008399544,0.0003327029,0.001020643,0.0002831887,0.0002621034],"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":[0.00003396339,0.00004025168,0.0000889165,0.00004809395,0.000140381,0.0002513505,0.001354814,0.9385918,0.0001212626,0.05873659,0.0001533139,0.0004392062],"study_design_scores_gemma":[0.0003911784,0.0001302987,0.00008247517,0.0000647001,0.0001167844,0.000003264154,0.00007979151,0.8934093,0.0003554765,0.1047416,0.0001244607,0.0005006898],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00360219,0.00004759438,0.9933619,0.000652467,0.0004221894,0.0004232831,0.0000113478,0.000218528,0.00126049],"genre_scores_gemma":[0.9341826,0.0001090683,0.06453032,0.0002642214,0.0001917426,0.000003373102,0.00004059142,0.00002962427,0.0006485026],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9305804,"threshold_uncertainty_score":0.9997635,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05696351284612938,"score_gpt":0.1735975240386822,"score_spread":0.1166340111925528,"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."}}