{"id":"W114980831","doi":"10.1007/978-3-662-43984-5_2","title":"Online Data Clustering Using Variational Learning of a Hierarchical Dirichlet Process Mixture of Dirichlet Distributions","year":2014,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Hierarchical Dirichlet process; Dirichlet process; Computer science; Dirichlet distribution; Cluster analysis; Generalized Dirichlet distribution; Hierarchical clustering; Latent Dirichlet allocation; Mixture model; Artificial intelligence; Data mining; Concentration parameter; Flexibility (engineering); Pattern recognition (psychology); Algorithm; Dirichlet's energy; Machine learning; Mathematics; Topic model; Statistics; Bayesian probability","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001686865,0.0004545043,0.0008288349,0.0006001585,0.0002204271,0.0001476106,0.004597502,0.0003684011,0.000009546019],"category_scores_gemma":[0.0004872914,0.0004137655,0.0001231327,0.0008649776,0.0006970444,0.000465965,0.002899345,0.00118029,8.233435e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001126742,"about_ca_system_score_gemma":0.0008153666,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002166,"about_ca_topic_score_gemma":0.00002498744,"domain_scores_codex":[0.9958925,0.0001485051,0.0008731625,0.001470836,0.001094338,0.0005206204],"domain_scores_gemma":[0.9960004,0.0008346697,0.0007518677,0.001773087,0.0004806992,0.0001592403],"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":[0.00002431484,0.0002083133,0.0001865869,0.0005148875,0.00006925005,0.00003143371,0.001272897,0.186032,0.0014432,0.1319079,0.0000155541,0.6782936],"study_design_scores_gemma":[0.0002013234,0.00009471874,0.0001227504,0.0005491875,0.00002385222,0.00005499271,1.063071e-7,0.8824409,0.0002972752,0.1156031,0.0002486885,0.0003630438],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001341363,0.0002538058,0.9979294,0.0004082743,0.0005522647,0.0002671213,0.0001523771,0.00005866097,0.0002439651],"genre_scores_gemma":[0.110247,0.00001696768,0.8890275,0.0001699362,0.0003567683,0.000001947224,0.0001152362,0.00002557315,0.00003905988],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6964089,"threshold_uncertainty_score":0.9998314,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03894781772483317,"score_gpt":0.3141210490527649,"score_spread":0.2751732313279317,"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."}}