{"id":"W2071709160","doi":"10.1162/neco_a_00311","title":"An Efficient Learning Procedure for Deep Boltzmann Machines","year":2012,"lang":"en","type":"article","venue":"Neural Computation","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":490,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Boltzmann machine; Restricted Boltzmann machine; MNIST database; Computer science; Artificial neural network; Artificial intelligence; Boltzmann constant; Deep belief network; Deep learning; Focus (optics); Inference; Algorithm; Hidden Markov model; Pattern recognition (psychology); Machine learning; Physics","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":[0.0014788,0.001307083,0.001157228,0.0009291273,0.0008029527,0.001150446,0.002382508,0.00157528,0.01064878],"category_scores_gemma":[0.006280991,0.001052604,0.001267512,0.001136243,0.001172995,0.001889674,0.002840961,0.003892736,0.003957119],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001238317,"about_ca_system_score_gemma":0.001501925,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002134066,"about_ca_topic_score_gemma":0.003400107,"domain_scores_codex":[0.9991309,0.000262743,0.00006645041,0.0001491802,0.0003081892,0.00008247764],"domain_scores_gemma":[0.9990883,0.0004798152,0.0000540817,0.0001350103,0.0001962768,0.00004648571],"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":[0.00007262533,0.00006418045,0.0003971471,0.0001866469,0.00008118858,0.0001062149,0.0001039453,0.5120466,0.005747373,0.25372,0.007117949,0.2203561],"study_design_scores_gemma":[0.00001608457,0.00001233188,0.00004374775,0.0000164523,0.000006595576,0.00003956817,0.000006754361,0.9006857,0.001492732,0.09269967,0.004968227,0.00001219052],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0003304986,0.00004549745,0.9984829,0.00005794541,0.00003249631,0.00002883927,0.00002877836,0.0003397774,0.0006532279],"genre_scores_gemma":[0.05517185,0.0002165039,0.9365003,0.0002111607,0.0001045441,0.0006010979,0.0003003822,0.0009242846,0.00596985],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01064878,"threshold_uncertainty_score":0.03562373,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01628468875810614,"score_gpt":0.2747265167593389,"score_spread":0.2584418280012328,"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."}}