{"id":"W2884286481","doi":"10.1109/tnnls.2018.2849932","title":"Multiclass Nonnegative Matrix Factorization for Comprehensive Feature Pattern Discovery","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks and Learning Systems","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"National Research Council Canada","keywords":"Computer science; Feature selection; Non-negative matrix factorization; Matrix decomposition; Artificial intelligence; Hyperparameter; Feature (linguistics); Machine learning; Pattern recognition (psychology); Data mining; Big data; Model selection; Class (philosophy)","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":[0.0000582184,0.0001482392,0.0001280436,0.00004070388,0.0003619838,0.00009686739,0.00006179073,0.0001558258,0.000002113322],"category_scores_gemma":[0.000005107514,0.0001271759,0.0000650388,0.00008126213,0.0000594392,0.00001338145,0.000001741596,0.0001864692,0.00000133392],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001310543,"about_ca_system_score_gemma":0.00001040503,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001622055,"about_ca_topic_score_gemma":0.0000120281,"domain_scores_codex":[0.9991506,0.0001330556,0.0001394821,0.0003230548,0.00008380892,0.0001699774],"domain_scores_gemma":[0.9995261,0.00004623492,0.0001030377,0.0001378705,0.0001280376,0.00005875086],"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":[0.0005197205,0.00007691611,0.0007244647,0.00008035744,0.0001241846,7.850098e-7,0.0003825387,0.6922796,0.2786976,0.00001465584,0.003029035,0.0240702],"study_design_scores_gemma":[0.001345525,0.001312215,0.001286259,0.00009851052,0.00004790248,0.00001557482,0.001185759,0.9357309,0.02232271,0.000001567308,0.03626996,0.0003830758],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.19053,0.0002177492,0.8076783,0.0001050925,0.001093441,0.0003166046,0.00001570809,0.00002935349,0.00001368437],"genre_scores_gemma":[0.9968597,0.00008213678,0.00005044705,0.0001074045,0.0005680653,0.00008380426,0.00004809285,0.00002493844,0.002175463],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8076279,"threshold_uncertainty_score":0.5186085,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01828226131322841,"score_gpt":0.2778320450856181,"score_spread":0.2595497837723897,"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."}}