{"id":"W2150529939","doi":"10.1145/1553374.1553506","title":"Using fast weights to improve persistent contrastive divergence","year":2009,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":281,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Markov chain; Computer science; Variance (accounting); Algorithm; Set (abstract data type); Divergence (linguistics); Markov chain Monte Carlo; Statistical physics; Artificial intelligence; Machine learning; Physics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.00009597028,0.0001366092,0.0001461563,0.00005524118,0.0001865231,0.0001405768,0.0004551686,0.00003142214,0.00004782154],"category_scores_gemma":[0.00002397175,0.0001075552,0.0001077953,0.0002542568,0.00001912964,0.0004015881,0.0001265758,0.00005562091,0.00006207648],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004342757,"about_ca_system_score_gemma":0.00003288729,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005186585,"about_ca_topic_score_gemma":0.000005494151,"domain_scores_codex":[0.9989361,0.00004059546,0.0001438525,0.0003977274,0.0001790345,0.0003027257],"domain_scores_gemma":[0.9993592,0.0000294139,0.00003959975,0.0002815886,0.0001224181,0.000167806],"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":[0.00006176467,0.000368709,0.0004024851,0.000005752197,0.0002003102,0.00006082099,0.003966183,0.05244835,0.3178361,0.07740699,0.004974374,0.5422682],"study_design_scores_gemma":[0.0002885472,0.0004629795,0.003048975,0.00002016704,0.00002610482,0.00000709545,0.0001492739,0.938066,0.0546247,0.001283121,0.00160365,0.0004194087],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006093201,0.00005712529,0.9869325,0.001117941,0.0004765966,0.0001771528,0.00000193288,0.00006249454,0.005081093],"genre_scores_gemma":[0.7989488,0.000002906735,0.1992152,0.001175457,0.0001356547,0.000001796999,2.480817e-7,0.000002681537,0.000517211],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8856176,"threshold_uncertainty_score":0.4385972,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02191974366862999,"score_gpt":0.2456868012082372,"score_spread":0.2237670575396072,"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."}}