{"id":"W3184159859","doi":"10.48550/arxiv.2107.12521","title":"Restricted Boltzmann Machine and Deep Belief Network: Tutorial and Survey","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Boltzmann machine; Restricted Boltzmann machine; Deep belief network; Graphical model; Gibbs sampling; Conditional random field; Artificial intelligence; Computer science; Belief propagation; Ising model; Divergence (linguistics); Artificial neural network; Boltzmann constant; Hidden Markov model; Markov chain Monte Carlo; Machine learning; Statistical physics; Algorithm; Physics; Bayesian probability","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004510161,0.0003763846,0.000485915,0.0001202843,0.0003157038,0.0004548277,0.0007545179,0.0003151101,0.00001793254],"category_scores_gemma":[0.000131916,0.0004201642,0.0001017323,0.0006316633,0.0001446187,0.0004173701,0.003228846,0.000538376,0.000003730352],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000654568,"about_ca_system_score_gemma":0.0001487877,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001406602,"about_ca_topic_score_gemma":0.001349938,"domain_scores_codex":[0.9972245,0.0006650267,0.0002236674,0.001346492,0.0001014054,0.0004389786],"domain_scores_gemma":[0.9981197,0.0003401382,0.0002085794,0.0008564414,0.0002324169,0.0002426925],"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":[0.0002405753,0.0002395852,0.06077638,0.0001277978,0.0007684267,0.001418226,0.0007065859,0.895312,0.0001082755,0.02426891,0.00281056,0.0132227],"study_design_scores_gemma":[0.0006732528,0.00006500708,0.071761,0.00006093139,0.000086195,0.000008286986,0.00002264739,0.9224633,0.00002774018,0.003357057,0.0008957433,0.0005788132],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1255389,0.001791255,0.8697128,0.00009151368,0.001981114,0.0002632095,0.00002470669,0.0001230373,0.0004734156],"genre_scores_gemma":[0.9914439,0.002080132,0.005407509,0.00008842579,0.0005000475,7.1062e-7,0.00006929499,0.0000188481,0.0003911018],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.865905,"threshold_uncertainty_score":0.999825,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04767065689551333,"score_gpt":0.1771218986617556,"score_spread":0.1294512417662422,"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."}}