{"id":"W193851967","doi":"","title":"Tempered Markov Chain Monte Carlo for training of Restricted Boltzmann Machines","year":2010,"lang":"en","type":"article","venue":"International Conference on Artificial Intelligence and Statistics","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":109,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Markov chain Monte Carlo; Boltzmann machine; Monte Carlo method; Computer science; Statistical physics; Markov chain; Markov chain mixing time; Parallel tempering; Boltzmann constant; Direct simulation Monte Carlo; Monte Carlo molecular modeling; Markov model; Markov property; Artificial intelligence; Dynamic Monte Carlo method; Mathematics; Physics; Machine learning; Artificial neural network; Statistics; Thermodynamics","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":[0.003406874,0.0009277733,0.002101623,0.0008719225,0.0007096873,0.001218929,0.002935122,0.002430764,0.005654731],"category_scores_gemma":[0.01808408,0.001580331,0.001069105,0.0010971,0.001778216,0.002002532,0.002627826,0.004225873,0.001533517],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001476998,"about_ca_system_score_gemma":0.00166798,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00723487,"about_ca_topic_score_gemma":0.007655044,"domain_scores_codex":[0.9984836,0.0009024758,0.00008126675,0.0001996438,0.0002077926,0.000125184],"domain_scores_gemma":[0.9902139,0.008127678,0.0002734652,0.0005700407,0.0005910483,0.0002237828],"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":[0.00007366829,0.00002031704,0.0002153335,0.00003957812,0.00003084588,0.00001502842,0.0000295279,0.9703234,0.0003833233,0.01205658,0.0004028486,0.01640946],"study_design_scores_gemma":[0.000004904186,0.000003920185,0.00001184782,0.000003391204,0.000001763688,0.000001974762,9.880578e-7,0.9958379,0.00009200556,0.003958816,0.00008047622,0.000002057674],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005363922,0.0002552696,0.9931422,0.0001011844,0.00003440846,0.00003535819,0.00003667047,0.0005054148,0.0005255668],"genre_scores_gemma":[0.4560996,0.0004541557,0.5371703,0.0002948514,0.0001364908,0.0007423394,0.0006205658,0.0006607294,0.003820973],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00723487,"threshold_uncertainty_score":0.0189169,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0921970941412643,"score_gpt":0.3253742672901905,"score_spread":0.2331771731489262,"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."}}