{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003072516,0.001621883,0.001235535,0.001051286,0.0006532512,0.001303073,0.002614526,0.001804445,0.003927217],"category_scores_gemma":[0.01462971,0.0007642636,0.0008859758,0.0006787792,0.001759481,0.003939357,0.004301649,0.003483105,0.001186244],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001210732,"about_ca_system_score_gemma":0.0009433932,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002044326,"about_ca_topic_score_gemma":0.002269577,"domain_scores_codex":[0.9988934,0.0003065058,0.00006597321,0.0001961059,0.0004130336,0.0001249691],"domain_scores_gemma":[0.9954165,0.002479392,0.0003525545,0.0009691095,0.0005802921,0.0002021932],"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":[0.0002668184,0.0001849077,0.001309362,0.000105701,0.0001008218,0.000139769,0.0001887896,0.7315833,0.01717083,0.09551349,0.002070943,0.1513653],"study_design_scores_gemma":[0.00001861915,0.00004544435,0.00006405375,0.000006571105,0.000008025482,0.0000276217,0.000005037914,0.9792625,0.002525737,0.01745149,0.0005751852,0.000009718023],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01525821,0.0001341514,0.9826973,0.0001152471,0.00005131697,0.0000366055,0.00001945383,0.0005642097,0.001123405],"genre_scores_gemma":[0.5953585,0.0003039735,0.3964142,0.0003580602,0.0001095014,0.000271251,0.0001796885,0.0007449191,0.006259961],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003927217,"threshold_uncertainty_score":0.01624918,"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."}}