{"id":"W2013035813","doi":"10.1162/neco_a_00142","title":"A Connection Between Score Matching and Denoising Autoencoders","year":2011,"lang":"en","type":"article","venue":"Neural Computation","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":980,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Autoencoder; Restricted Boltzmann machine; Artificial intelligence; Noise reduction; Pattern recognition (psychology); Estimator; Computer science; Matching (statistics); Probabilistic logic; Unsupervised learning; Nonparametric statistics; Energy (signal processing); Rank (graph theory); Artificial neural network; Machine learning; Mathematics; Statistics","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":[],"consensus_categories":[],"category_scores_codex":[0.0001275268,0.00009158936,0.0001012105,0.0000675512,0.0001922963,0.0001285571,0.0001188664,0.00003174547,0.000003058563],"category_scores_gemma":[0.00001453857,0.00008704609,0.00002577838,0.0001558125,0.00002654358,0.0006935199,0.000074557,0.00007822394,0.000005263392],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001626941,"about_ca_system_score_gemma":0.00001028869,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001155603,"about_ca_topic_score_gemma":0.000008610305,"domain_scores_codex":[0.9992864,0.00009212625,0.0001366195,0.0002424212,0.0001049893,0.0001374405],"domain_scores_gemma":[0.9996639,0.00007570913,0.00007411301,0.00008634574,0.00004819922,0.00005171075],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002562349,0.0000517959,0.02326751,0.00004204013,0.00007012031,0.00002879417,0.01347803,0.09588788,0.006404745,0.007250996,0.0002376217,0.8532549],"study_design_scores_gemma":[0.0002499283,0.0001225293,0.1546903,0.00002255626,0.00001521457,0.00001719558,0.00009327009,0.818454,0.002803896,0.02331803,0.00001776954,0.0001953062],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.367521,0.00002139774,0.6318885,0.0001011634,0.000146921,0.00005920463,2.598728e-7,0.00007646799,0.0001850513],"genre_scores_gemma":[0.9343232,0.000002009131,0.06545926,0.0001150609,0.0000849249,0.000001897373,0.000002369745,0.000005681586,0.000005584167],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8530595,"threshold_uncertainty_score":0.3549637,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06044979363662861,"score_gpt":0.2499212846951548,"score_spread":0.1894714910585262,"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."}}