{"id":"W2103605202","doi":"10.1109/cvpr.2005.493","title":"MML-Based Approach for High-Dimensional Unsupervised Learning Using the Generalized Dirichlet Mixture","year":2006,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Hierarchical Dirichlet process; Dirichlet distribution; Generalized Dirichlet distribution; Minimum description length; Cluster analysis; Pattern recognition (psychology); Mathematics; Expectation–maximization algorithm; Latent Dirichlet allocation; Dimensionality reduction; Computer science; Concentration parameter; Artificial intelligence; Algorithm; Applied mathematics; Topic model; Statistics; Dirichlet's principle; Maximum likelihood","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":[0.0006316898,0.0001742179,0.0001790974,0.00006094127,0.000397754,0.0001649312,0.0005263058,0.0001032278,0.00002033137],"category_scores_gemma":[0.00002259535,0.0001108894,0.0001319573,0.0002952369,0.00004466855,0.0001406178,0.00009419721,0.0001682647,0.000001330491],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002068953,"about_ca_system_score_gemma":0.00008486215,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000197556,"about_ca_topic_score_gemma":0.000003907015,"domain_scores_codex":[0.9985413,0.000242224,0.000210822,0.0004179763,0.0002554244,0.0003322559],"domain_scores_gemma":[0.9992067,0.0001583739,0.00007685274,0.0004065523,0.00009821313,0.00005334887],"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":[0.0000313386,0.0001128477,0.00005954898,0.00002634269,0.00002538126,0.000003694369,0.00007325617,0.1212638,0.02136622,0.8423642,0.005223293,0.009450063],"study_design_scores_gemma":[0.0007600602,0.00003063371,0.00004894448,0.000004863878,0.00001625777,0.000007256018,0.00000235138,0.973636,0.009176267,0.01488703,0.001246714,0.0001836252],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006836434,0.0001755207,0.9905249,0.0008728877,0.0001552869,0.0002636883,0.000002239859,0.0001402287,0.001028774],"genre_scores_gemma":[0.1675855,4.325237e-7,0.830192,0.001286574,0.0001878902,0.00003028892,0.00002155618,0.00001589192,0.0006798651],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8523722,"threshold_uncertainty_score":0.452194,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02303602396394006,"score_gpt":0.2568860463962997,"score_spread":0.2338500224323597,"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."}}