{"id":"W2054814877","doi":"10.1109/cvpr.2012.6247936","title":"Robust Boltzmann Machines for recognition and denoising","year":2012,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":172,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Restricted Boltzmann machine; Artificial intelligence; Computer science; Noise reduction; Boltzmann machine; Pattern recognition (psychology); Noise (video); Unsupervised learning; Pixel; Mixture model; Inference; Image (mathematics); Computer vision; Machine learning; Deep learning","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":[0.0001980737,0.00006099609,0.00006440724,0.00002690476,0.0001150081,0.00009710292,0.00008364118,0.00002203142,0.00001506543],"category_scores_gemma":[0.00003467228,0.00004831212,0.00002332514,0.00005844163,0.00001274556,0.0007094464,0.00005414097,0.00002185534,0.00001324116],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005518449,"about_ca_system_score_gemma":0.000004269844,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001890435,"about_ca_topic_score_gemma":0.000007241873,"domain_scores_codex":[0.9995683,0.00002329699,0.00007168335,0.0001229785,0.0000445785,0.0001691434],"domain_scores_gemma":[0.9997088,0.0000785354,0.00002383396,0.00009324502,0.00003811859,0.00005743692],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000009859644,0.0000685595,0.001562483,0.00001972509,0.00002990156,4.409171e-7,0.00063349,0.000362958,0.008198063,0.008264557,0.007257631,0.9735923],"study_design_scores_gemma":[0.001172962,0.0001971277,0.0135437,0.00004972724,0.00006091779,0.0000471626,0.0001332086,0.8575205,0.07321258,0.02789564,0.02525498,0.0009115311],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008063163,0.0002741196,0.9894739,0.0003977059,0.0002527496,0.00009820164,0.000001656996,0.00004387424,0.001394654],"genre_scores_gemma":[0.6123751,0.00001189717,0.3866389,0.0003391109,0.0003586609,0.00001033321,0.00000343535,0.000004737306,0.0002577896],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9726808,"threshold_uncertainty_score":0.1970111,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06998329453687235,"score_gpt":0.2443677109825801,"score_spread":0.1743844164457078,"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."}}