{"id":"W2907883156","doi":"10.1109/icbk.2018.00054","title":"Principal Sample Analysis for Data Reduction","year":2018,"lang":"en","type":"article","venue":"","topic":"Machine Learning and ELM","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Dimensionality reduction; Computer science; Reduction (mathematics); Discriminative model; Sample (material); Principal component analysis; Data reduction; Artificial intelligence; MNIST database; Data mining; Pattern recognition (psychology); Generalizability theory; Preprocessor; Sample size determination; Population; Machine learning; Statistics; Mathematics; 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":[0.005106025,0.002160407,0.001900212,0.003374963,0.001198622,0.00260495,0.001793993,0.001148036,0.009330102],"category_scores_gemma":[0.02608994,0.0007655764,0.002551064,0.005041657,0.001687444,0.00259541,0.003034892,0.003958298,0.006768376],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000865059,"about_ca_system_score_gemma":0.002716891,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001931843,"about_ca_topic_score_gemma":0.00203463,"domain_scores_codex":[0.9931372,0.001994197,0.0006284588,0.001287512,0.002725632,0.0002270535],"domain_scores_gemma":[0.990208,0.004048438,0.0005865358,0.003005358,0.002008259,0.0001434325],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003045037,0.0002077823,0.002949721,0.00107886,0.0004216219,0.0002161121,0.0004189686,0.03297584,0.01636027,0.06326243,0.03244819,0.8493557],"study_design_scores_gemma":[0.0001406002,0.0004089244,0.006435496,0.0003070442,0.0002673963,0.0009603746,0.0005724428,0.5944099,0.04432522,0.1777861,0.1741645,0.000221832],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001332875,0.0004081376,0.9952443,0.0002207721,0.0001116185,0.0001704814,0.0004641209,0.001295156,0.0007525781],"genre_scores_gemma":[0.02220679,0.0007050994,0.9718665,0.0001867763,0.0001907175,0.000838517,0.001900743,0.0004142511,0.00169072],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009330102,"threshold_uncertainty_score":0.03121227,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06993294597854288,"score_gpt":0.3436422628736149,"score_spread":0.273709316895072,"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."}}