{"id":"W3159094249","doi":"10.1109/tnnls.2021.3071083","title":"Maximum <i>A Posteriori</i> Approximation of Hidden Markov Models for Proportional Sequential Data Modeling With Simultaneous Feature Selection","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks and Learning Systems","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds de recherche du Québec","keywords":"Hidden Markov model; Maximum a posteriori estimation; Computer science; Artificial intelligence; Pattern recognition (psychology); Inference; Feature (linguistics); A priori and a posteriori; Dirichlet process; Feature selection; Machine learning; Focus (optics); Prior probability; Model selection; Speech recognition; Maximum likelihood; Mathematics; Bayesian probability; Statistics","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":[0.0002377776,0.0001632244,0.0002149406,0.00008451603,0.0004299279,0.0002304244,0.0001633189,0.0001171392,0.000003305563],"category_scores_gemma":[0.000004728899,0.0001458091,0.00005222311,0.0002227085,0.00002161577,0.0007582677,0.00000579251,0.0003876656,4.141557e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000278732,"about_ca_system_score_gemma":0.0000573907,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002731454,"about_ca_topic_score_gemma":0.00002256421,"domain_scores_codex":[0.9986042,0.0001703371,0.0002853884,0.0004835539,0.0002529937,0.000203552],"domain_scores_gemma":[0.9991007,0.0001244359,0.0001766407,0.0002380841,0.0002973482,0.00006282785],"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":[0.00009475106,0.00004680254,0.000002204254,0.00008776628,0.00004488361,0.000005809386,0.00008592579,0.9545292,0.0005059118,0.00008123786,0.00001996408,0.04449551],"study_design_scores_gemma":[0.0004611294,0.0002337924,0.00000123411,0.0001239883,0.00004805067,0.0002754979,0.00007657742,0.9982348,0.0002526309,0.00004755531,0.00007962631,0.0001650907],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02312206,0.0001408653,0.9755585,0.0001514648,0.0004809593,0.0003800903,0.0000209556,0.0001152752,0.00002985861],"genre_scores_gemma":[0.9924245,0.00004408957,0.006850286,0.00004793456,0.0001656762,0.00004191211,0.00009892281,0.00001968008,0.0003069445],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9693025,"threshold_uncertainty_score":0.5945922,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02986876484036317,"score_gpt":0.2442255362818822,"score_spread":0.2143567714415191,"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."}}