{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002765633,0.0001533968,0.0001989023,0.0001319117,0.0001186665,0.0001904525,0.0005074232,0.00006807501,0.00007244058],"category_scores_gemma":[0.0007862357,0.0001398412,0.0000453419,0.0001156508,0.0001496784,0.0001767307,0.00007343703,0.0001640173,0.000004648874],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009849319,"about_ca_system_score_gemma":0.00009242984,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001137877,"about_ca_topic_score_gemma":0.0003547971,"domain_scores_codex":[0.9987757,0.000051809,0.0004062986,0.000327701,0.0002462465,0.0001922035],"domain_scores_gemma":[0.9984714,0.000541675,0.0001720759,0.0002031046,0.0005316928,0.00008004659],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006749313,0.00004484468,0.00002979235,0.000005369207,0.00002492884,0.000003560923,0.0006487055,0.0004325627,0.01391554,0.6157774,0.0002102372,0.3688395],"study_design_scores_gemma":[0.00005242021,0.0001737919,0.0003180912,0.00002424936,0.00000754367,0.000003944853,0.0002682314,0.9033294,0.007051245,0.08817594,0.0004358801,0.0001592686],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007162992,0.000009414968,0.9887243,0.001231068,0.001134171,0.0001905264,0.000289495,0.00002587744,0.001232161],"genre_scores_gemma":[0.8271466,0.00004065939,0.1723546,0.00009320805,0.0001630629,0.00001883371,0.00001464418,0.000007062277,0.0001612667],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9028968,"threshold_uncertainty_score":0.570256,"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."}}