{"id":"W2162747531","doi":"","title":"Generative versus discriminative training of RBMs for classification of fMRI images","year":2008,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":65,"is_retracted":false,"has_abstract":true,"ca_institutions":"Baycrest Hospital; University of Toronto","funders":"","keywords":"Discriminative model; Overfitting; Artificial intelligence; Computer science; Pattern recognition (psychology); Generative model; Voxel; Machine learning; Set (abstract data type); Training set; Data set; Task (project management); Generative grammar; Artificial neural network","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":[0.00016518,0.0001023526,0.0002167774,0.00006634507,0.0001035085,0.00001187149,0.0003019024,0.00003423496,0.00001241493],"category_scores_gemma":[0.0001350362,0.00008262858,0.00009809782,0.0001936158,0.0001644555,0.0003796203,0.00005247963,0.00003637869,0.000001083262],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001684595,"about_ca_system_score_gemma":0.00007585647,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000261826,"about_ca_topic_score_gemma":0.00001162623,"domain_scores_codex":[0.9991434,0.00006801205,0.000253888,0.0002395965,0.000148876,0.0001462623],"domain_scores_gemma":[0.998915,0.0003368083,0.0001844316,0.0002313832,0.0002967264,0.00003571265],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002849468,0.0003462288,0.0001815217,0.00005314807,0.0002900774,0.000003241934,0.03105486,0.004180367,0.5465555,0.2286749,0.00911055,0.1792646],"study_design_scores_gemma":[0.001216012,0.0005299998,0.005120534,0.00001495993,0.00002427112,0.000001865219,0.00258475,0.2822419,0.706122,0.001646705,0.0002932361,0.0002038284],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007063915,0.0000460612,0.9870961,0.0005647089,0.0002294357,0.000204937,0.00001155295,0.00001971527,0.004763628],"genre_scores_gemma":[0.745669,0.00001516459,0.2540242,0.00001594998,0.00005298399,0.00001940893,0.000003889336,0.000004317406,0.0001950854],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7386051,"threshold_uncertainty_score":0.3369496,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1259106268912469,"score_gpt":0.297985180630316,"score_spread":0.1720745537390691,"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."}}