{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001580857,0.001120655,0.0006418334,0.0005026919,0.000318574,0.000919887,0.00111718,0.001255315,0.002553003],"category_scores_gemma":[0.004815245,0.0007576459,0.0008843169,0.0004390518,0.002247993,0.001757463,0.001926637,0.002786992,0.0005976281],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001335101,"about_ca_system_score_gemma":0.000817,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0025267,"about_ca_topic_score_gemma":0.002950331,"domain_scores_codex":[0.9992384,0.0003529371,0.00002309493,0.0001767644,0.0001593553,0.00004944672],"domain_scores_gemma":[0.9984861,0.001085723,0.0001079391,0.0001692547,0.00009247881,0.00005847704],"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":[0.00004785178,0.00003248184,0.0003106295,0.00005381183,0.00005196526,0.00008837946,0.00009478197,0.5910582,0.005090798,0.3770499,0.001920374,0.02420072],"study_design_scores_gemma":[0.000003380324,0.00001047191,0.000048454,0.00000813207,0.000004412841,0.00001666552,0.000003985161,0.9221037,0.001105706,0.07587911,0.0008091938,0.000006781683],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004619736,0.0001236269,0.9922847,0.0002306937,0.00002629693,0.00001138578,0.00003425452,0.0001607215,0.002508575],"genre_scores_gemma":[0.6484702,0.0008663824,0.3284965,0.0005827476,0.0002296911,0.0001864002,0.0002946925,0.0006581922,0.02021528],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002553003,"threshold_uncertainty_score":0.009686887,"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."}}