{"id":"W4387504521","doi":"10.1016/j.patcog.2023.110037","title":"A topic modeling and image classification framework: The Generalized Dirichlet variational autoencoder","year":2023,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Topic Modeling","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Latent Dirichlet allocation; Autoencoder; Topic model; Dirichlet distribution; Computer science; Covariance; Inference; Artificial intelligence; Generative model; Latent variable; Representation (politics); Benchmark (surveying); Code (set theory); Pattern recognition (psychology); Machine learning; Artificial neural network; Mathematics; Generative grammar; Statistics; Set (abstract data type); Boundary value problem","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003438775,0.0008249883,0.002124887,0.001632729,0.0005967052,0.002043329,0.002583181,0.002157287,0.001664832],"category_scores_gemma":[0.007958892,0.0008097038,0.001833404,0.002128939,0.001225501,0.002514407,0.001659111,0.002869256,0.000618645],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001325262,"about_ca_system_score_gemma":0.001300614,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00829565,"about_ca_topic_score_gemma":0.007864736,"domain_scores_codex":[0.9982734,0.0008667777,0.00007098177,0.0004021835,0.0002596249,0.0001271074],"domain_scores_gemma":[0.9972076,0.002042975,0.0001503048,0.000229694,0.0002780854,0.00009136658],"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":[0.0002147756,0.0001775569,0.002425738,0.000363258,0.0004369403,0.0001315426,0.000428798,0.5153643,0.005040273,0.2151921,0.00970263,0.2505221],"study_design_scores_gemma":[0.000007319317,0.0000123316,0.0002064743,0.00001282339,0.00001990462,0.00002581924,0.00001142062,0.9592484,0.0002841568,0.03905488,0.001105156,0.00001128637],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005340457,0.001001335,0.9923644,0.0004567257,0.0000740185,0.00002575852,0.0001286311,0.0001189365,0.000489855],"genre_scores_gemma":[0.4789864,0.004983824,0.5018767,0.0007536751,0.001333343,0.0004443605,0.001667385,0.000436166,0.009518226],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00829565,"threshold_uncertainty_score":0.01818615,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08430624976072619,"score_gpt":0.2919918592378226,"score_spread":0.2076856094770964,"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."}}