{"id":"W2964327378","doi":"","title":"Analysis of semi-supervised learning with the Yarowsky algorithm","year":2007,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":45,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Weighted Majority Algorithm; Computer science; Algorithm; Semi-supervised learning; Supervised learning; Graph; Bootstrapping (finance); Artificial intelligence; Entropy (arrow of time); Machine learning; Unsupervised learning; Wake-sleep algorithm; Mathematics; Theoretical computer science; Generalization error; Artificial neural network","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":[0.01216987,0.001187264,0.002200155,0.003057339,0.001181528,0.002880944,0.003495286,0.001938944,0.003956215],"category_scores_gemma":[0.04166783,0.001144703,0.001498424,0.002513026,0.003822528,0.006165905,0.003370461,0.003517855,0.0008699347],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002527653,"about_ca_system_score_gemma":0.002035281,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002516012,"about_ca_topic_score_gemma":0.001995478,"domain_scores_codex":[0.990506,0.004117185,0.0004105317,0.001288049,0.003327443,0.0003508044],"domain_scores_gemma":[0.9599342,0.03030188,0.002650017,0.002018487,0.004508174,0.0005870988],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001484437,0.00007366073,0.001776858,0.0002871047,0.0002007003,0.0001505157,0.0003597115,0.4714723,0.001510434,0.4517528,0.002441987,0.06982544],"study_design_scores_gemma":[0.000008021335,0.00001814264,0.0002177515,0.00002122537,0.00000876798,0.00002490057,0.00001467819,0.8729832,0.0003128205,0.1257028,0.0006751779,0.00001244128],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004233357,0.0003287196,0.9943336,0.000139708,0.0000150326,0.00003148054,0.00003227552,0.0001235539,0.0007622921],"genre_scores_gemma":[0.3922475,0.001344302,0.5979729,0.0003422401,0.000327865,0.0006137916,0.0007119896,0.0004979736,0.005941477],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01216987,"threshold_uncertainty_score":0.06436116,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00397787480399339,"score_gpt":0.2359396683324911,"score_spread":0.2319617935284977,"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."}}