{"id":"W2064630666","doi":"10.1162/neco.2008.04-07-510","title":"Representational Power of Restricted Boltzmann Machines and Deep Belief Networks","year":2008,"lang":"en","type":"article","venue":"Neural Computation","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":839,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Boltzmann machine; Deep belief network; Restricted Boltzmann machine; Artificial intelligence; Block (permutation group theory); Artificial neural network; Inference; Probabilistic logic; Computer science; Deep learning; Generative model; Boltzmann constant; Power (physics); Machine learning; Generative grammar; Theoretical computer science; Mathematics","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":[0.00006019807,0.0001006219,0.0001348638,0.00007649858,0.0001605759,0.0000380114,0.0001563491,0.00003832666,0.000006094457],"category_scores_gemma":[0.00004621413,0.00009190133,0.00003966279,0.0003144181,0.00006975038,0.0004028658,0.00009933245,0.00007933594,0.000001628778],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000798166,"about_ca_system_score_gemma":0.00001510824,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003873924,"about_ca_topic_score_gemma":0.000004021493,"domain_scores_codex":[0.9990759,0.0001137325,0.0002256536,0.0002578928,0.0001966666,0.000130139],"domain_scores_gemma":[0.9993596,0.0001773706,0.0001256254,0.0001374484,0.000149306,0.00005063664],"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":[0.00003837966,0.00007458568,0.009501885,0.000007108506,0.00003150289,0.00002911709,0.0009652235,0.9329822,0.002046608,0.001616705,0.001790727,0.05091596],"study_design_scores_gemma":[0.0002154338,0.00007185451,0.1710982,0.000003410594,0.000003305739,0.00002998533,0.000006189799,0.8277473,0.0001975779,0.0005234829,0.000028379,0.0000748677],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2396715,0.0002633251,0.7591361,0.0003228001,0.0002339297,0.00009664597,9.231556e-7,0.00004491628,0.0002298843],"genre_scores_gemma":[0.9735461,0.00003638231,0.02614092,0.0001470191,0.0000803973,0.000003177591,0.00001239307,0.000005578016,0.00002804345],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7338746,"threshold_uncertainty_score":0.3747628,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0162958313026846,"score_gpt":0.2431024191057949,"score_spread":0.2268065878031103,"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."}}