{"id":"W2164700406","doi":"10.1146/annurev-statistics-010814-020120","title":"Learning Deep Generative Models","year":2015,"lang":"en","type":"article","venue":"Annual Review of Statistics and Its Application","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":448,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Office of Naval Research; Samsung; Canadian Institute for Advanced Research","keywords":"Deep belief network; Boltzmann machine; Artificial intelligence; Computer science; Deep learning; Generative grammar; Feature (linguistics); Generative model; Object (grammar); Machine learning; Perception; Restricted Boltzmann machine; Cognitive neuroscience of visual object recognition","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002158509,0.00007180304,0.0001420932,0.00001597475,0.00005606543,0.00001741359,0.0001785844,0.00001887165,0.000001351765],"category_scores_gemma":[0.0000345663,0.00006093665,0.00001336016,0.0001779877,0.00001844319,0.0002000882,0.00007878392,0.00006399101,0.00001018101],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007906233,"about_ca_system_score_gemma":0.00002518427,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007499249,"about_ca_topic_score_gemma":0.00000137763,"domain_scores_codex":[0.999329,0.00003170029,0.000217703,0.0001877182,0.0001461815,0.00008770268],"domain_scores_gemma":[0.999184,0.00004730299,0.0001524779,0.0001576743,0.0003729574,0.00008564398],"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":[4.813368e-7,0.00001403504,0.000003348236,0.0001721333,0.000003047446,1.620395e-7,0.000185277,0.0003907814,0.00004755585,0.7908121,0.002378186,0.2059929],"study_design_scores_gemma":[0.0001130279,0.0001155874,0.00006498656,0.0002121954,0.00001650681,0.00000484923,0.00004424899,0.8756843,0.0001563891,0.07047569,0.05297009,0.0001421814],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0001229119,0.01988334,0.9780706,0.0007121666,0.00001444305,0.0002860591,0.0000286927,0.00002049236,0.0008612956],"genre_scores_gemma":[0.568473,0.1750605,0.2532554,0.002201829,0.0001381825,0.0003296364,0.0001644963,0.00002055209,0.0003564227],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8752935,"threshold_uncertainty_score":0.2484924,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02706827500576708,"score_gpt":0.2962983746660544,"score_spread":0.2692300996602873,"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."}}