{"id":"W2891477799","doi":"","title":"Deep Homogeneous Mixture Models: Representation, Separation, and Approximation","year":2018,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Representation (politics); Connection (principal bundle); Constant (computer programming); Computer science; Mixture model; Homogeneous; Exponential function; Tree (set theory); Graphical model; Algorithm; Mathematics; Exponential growth; Latent variable; Artificial intelligence; Pattern recognition (psychology); Combinatorics; Mathematical analysis","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003722806,0.0001547825,0.0001651234,0.0001603928,0.0003939415,0.001174481,0.0002848517,0.0001085261,0.000001488999],"category_scores_gemma":[0.00004361331,0.0001329365,0.00002626614,0.0004545451,0.00006076789,0.007490315,0.0000695952,0.00009726616,0.00001700468],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002980317,"about_ca_system_score_gemma":0.00005201195,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002048378,"about_ca_topic_score_gemma":0.000002681409,"domain_scores_codex":[0.9986421,0.0001055111,0.0005045759,0.0002307748,0.000316118,0.0002008568],"domain_scores_gemma":[0.9986354,0.0000269658,0.0003379481,0.0003076974,0.0006045756,0.00008745722],"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":[0.00002250902,0.00002512178,0.00007027526,0.0004422502,0.00001833077,0.000001898961,0.02502991,0.01029721,0.0004788312,0.148872,0.002626376,0.8121153],"study_design_scores_gemma":[0.0001882018,0.00004329669,0.00004203256,0.0000337429,0.000005755654,0.0001477502,0.0001076486,0.9873626,0.0004939223,0.01013316,0.001284498,0.000157348],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002013364,0.0004582345,0.9915292,0.0003776147,0.0004303922,0.0003380011,0.000001380881,0.000252232,0.004599635],"genre_scores_gemma":[0.8507797,0.00001247394,0.1482344,0.0005239935,0.0002172644,0.00005555687,0.00002152066,0.00000769761,0.0001474162],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9770654,"threshold_uncertainty_score":0.9998624,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02601520224338223,"score_gpt":0.2934103046597554,"score_spread":0.2673951024163732,"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."}}