{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001488537,0.0006693613,0.0006465585,0.0009921845,0.0005268672,0.0006467602,0.004058562,0.0003713288,0.00003178175],"category_scores_gemma":[0.0007868108,0.0005822963,0.0002003297,0.0009264885,0.0004386308,0.0003248147,0.0003617693,0.0006396766,0.00002193706],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004945844,"about_ca_system_score_gemma":0.0006076694,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003887241,"about_ca_topic_score_gemma":0.00004036055,"domain_scores_codex":[0.9952403,0.00007634667,0.0005575608,0.002337837,0.001000308,0.0007875962],"domain_scores_gemma":[0.9934075,0.00362655,0.0003535115,0.002047178,0.0003254025,0.0002398081],"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":[0.00002988511,0.0000874488,0.00001202096,0.00002068302,0.00000644335,0.000004539853,0.0004818386,0.5728508,0.0002472931,0.05610764,0.000006678012,0.3701447],"study_design_scores_gemma":[0.0005689156,0.000863664,0.0001352984,0.0001614874,0.00001377757,0.000002519133,5.214604e-7,0.6963485,0.01214896,0.2886088,0.0005577931,0.000589768],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001165926,0.00004431591,0.9937164,0.00283175,0.000809225,0.001416069,0.00007324028,0.0007205372,0.0002718455],"genre_scores_gemma":[0.1302589,0.00000362125,0.8684818,0.0009779336,0.0001038419,0.00009364461,0.000006837886,0.00003765355,0.0000358601],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3695549,"threshold_uncertainty_score":0.9996629,"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."}}