{"id":"W2165398449","doi":"10.1186/1748-7188-5-38","title":"Efficient algorithms for training the parameters of hidden Markov models using stochastic expectation maximization (EM) training and Viterbi training","year":2010,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Viterbi algorithm; Computer science; Hidden Markov model; Iterative Viterbi decoding; Forward algorithm; Markov model; Markov chain; Soft output Viterbi algorithm; Expectation–maximization algorithm; Training (meteorology); Machine learning; Algorithm; Maximum-entropy Markov model; Artificial intelligence; Variable-order Markov model; Maximum likelihood; Decoding methods; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003630829,0.002072046,0.001296947,0.001503747,0.0008566525,0.001361012,0.003727309,0.002415516,0.007979573],"category_scores_gemma":[0.02424678,0.001398477,0.0009918181,0.001530784,0.001119161,0.002701932,0.002351399,0.004315391,0.003582554],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001645142,"about_ca_system_score_gemma":0.002626404,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005618033,"about_ca_topic_score_gemma":0.00728459,"domain_scores_codex":[0.9980111,0.0009002439,0.0001687575,0.0004244826,0.0003858068,0.0001096458],"domain_scores_gemma":[0.9899853,0.008199654,0.0004249411,0.0005863508,0.0006964695,0.0001072127],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001452482,0.0001275811,0.001120786,0.0002611544,0.0001164384,0.00007787695,0.0001942891,0.5383762,0.003098573,0.03640476,0.005655903,0.4144213],"study_design_scores_gemma":[0.00002131052,0.00001381201,0.00009528042,0.00002253814,0.00001097993,0.00003705929,0.00001307091,0.9762873,0.001993031,0.01996518,0.001527601,0.00001280744],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0009747596,0.0001090931,0.9974887,0.00007907666,0.00001640422,0.00003270737,0.00003343339,0.0009165839,0.0003492238],"genre_scores_gemma":[0.03777816,0.0002383267,0.9593405,0.0001331633,0.00004751924,0.0003824707,0.0003859993,0.0004154465,0.001278475],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007979573,"threshold_uncertainty_score":0.0266943,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07937526116788873,"score_gpt":0.3143771748915459,"score_spread":0.2350019137236571,"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."}}