{"id":"W1569526680","doi":"10.1007/978-3-540-30115-8_27","title":"An Efficient Method to Estimate Labelled Sample Size for Transductive LDA(QDA/MDA) Based on Bayes Risk","year":2004,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"University of Toronto","keywords":"Computer science; Artificial intelligence; Machine learning; Gaussian; Linear discriminant analysis; Bayes' theorem; Supervised learning; Bayesian probability; Sample size determination; Semi-supervised learning; Pattern recognition (psychology); Sample (material); Mathematics; Statistics; Artificial neural network","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":[0.009699789,0.001364625,0.003149256,0.002087889,0.001422312,0.002219002,0.002849228,0.002109974,0.003751587],"category_scores_gemma":[0.0365011,0.001197519,0.001728731,0.001200552,0.001320775,0.00366064,0.003175874,0.003817026,0.001901064],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001637299,"about_ca_system_score_gemma":0.002181638,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002569643,"about_ca_topic_score_gemma":0.004214403,"domain_scores_codex":[0.9933078,0.003124812,0.0004312477,0.001065043,0.001867361,0.0002037216],"domain_scores_gemma":[0.9828388,0.01160158,0.0005034796,0.001975585,0.002818332,0.0002622078],"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":[0.0004033383,0.0002728018,0.002811734,0.0003075149,0.0002767193,0.00008419526,0.0003547574,0.1106349,0.0167259,0.04214327,0.006920399,0.8190645],"study_design_scores_gemma":[0.00004042211,0.00006653009,0.0007359458,0.00003419529,0.00004957095,0.000108869,0.00002972358,0.9523293,0.004105156,0.04046067,0.001991976,0.00004770443],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001425538,0.00009089401,0.9977702,0.00004238852,0.00003002622,0.00005181958,0.00002688313,0.0004268726,0.0001354272],"genre_scores_gemma":[0.05182709,0.0001235685,0.9460636,0.0000963026,0.0001004978,0.0004506285,0.0002544241,0.0002718865,0.0008120036],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009699789,"threshold_uncertainty_score":0.05129802,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01777159948065452,"score_gpt":0.3131416018898215,"score_spread":0.295370002409167,"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."}}