{"id":"W2107215445","doi":"10.1109/ita.2010.5454138","title":"A tutorial on stochastic approximation algorithms for training Restricted Boltzmann Machines and Deep Belief Nets","year":2010,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":62,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Boltzmann machine; MNIST database; Restricted Boltzmann machine; Deep belief network; Computer science; Boltzmann constant; Artificial intelligence; Divergence (linguistics); Classifier (UML); Algorithm; Belief propagation; Training set; Machine learning; Artificial neural network; Mathematical optimization; Mathematics","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":[0.0002011896,0.0001463822,0.0001561094,0.00008300682,0.00022454,0.0002254125,0.0002404342,0.00007709049,0.000009165841],"category_scores_gemma":[0.0002532177,0.0001174376,0.00004294326,0.0001625846,0.00003621744,0.000334284,0.00006439382,0.0001314479,0.000003388328],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008174917,"about_ca_system_score_gemma":0.00003191045,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003068226,"about_ca_topic_score_gemma":0.00004645886,"domain_scores_codex":[0.9990332,0.00003472446,0.0001738762,0.0003647701,0.0001553792,0.0002381093],"domain_scores_gemma":[0.999231,0.0002919303,0.00006944119,0.0002316764,0.00008609335,0.00008984758],"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":[0.00005713381,0.00009468196,0.00000874578,0.000009454304,0.00003754857,0.000002247066,0.001766623,0.007002284,0.01531825,0.06146774,0.001101819,0.9131335],"study_design_scores_gemma":[0.0005972272,0.0001831472,0.0003928794,0.000005908338,0.000008135721,0.000004788129,0.00001953719,0.9919466,0.0005196715,0.005130621,0.001033931,0.0001576037],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004434772,0.00001763211,0.992162,0.0006636623,0.001699899,0.000357482,0.000003312494,0.000102832,0.0005583456],"genre_scores_gemma":[0.6051745,0.000001935291,0.3931288,0.000226406,0.001245894,0.00006018234,0.000009366951,0.00001205123,0.000140861],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9849443,"threshold_uncertainty_score":0.4788967,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02284832176213295,"score_gpt":0.2543777874259113,"score_spread":0.2315294656637784,"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."}}