{"id":"W4382063067","doi":"10.3390/math11132819","title":"Active Learning: Encoder-Decoder-Outlayer and Vector Space Diversification Sampling","year":2023,"lang":"en","type":"article","venue":"Mathematics","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Pipeline (software); Encoder; Sampling (signal processing); Flexibility (engineering); Machine learning; Diversification (marketing strategy); Artificial intelligence; Sample (material); Computer engineering; Data mining; Mathematics; Computer vision","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":[0.002731393,0.001662399,0.001387674,0.0008230958,0.0006559563,0.00163086,0.003160847,0.001880023,0.004403513],"category_scores_gemma":[0.00947374,0.0008837896,0.0007486566,0.0008670276,0.001170979,0.002710073,0.003095778,0.002866314,0.001784112],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008993093,"about_ca_system_score_gemma":0.002110064,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004157028,"about_ca_topic_score_gemma":0.006176422,"domain_scores_codex":[0.9985085,0.0005975256,0.00007616213,0.0003725374,0.0003026795,0.000142477],"domain_scores_gemma":[0.9974467,0.001337689,0.0001151329,0.0004933508,0.0004564472,0.0001507592],"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":[0.0007206014,0.0003299782,0.002481626,0.0001904697,0.0001188416,0.0001930528,0.0003143112,0.2808838,0.01051204,0.04622705,0.008676102,0.6493521],"study_design_scores_gemma":[0.00003302554,0.00007004413,0.00009272085,0.00001062731,0.00001098681,0.0000482427,0.00001558927,0.9843484,0.003583769,0.01029443,0.001480956,0.00001121627],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005751184,0.0001911425,0.9914263,0.0001269766,0.00004518314,0.00008407226,0.00005185616,0.001408583,0.0009146124],"genre_scores_gemma":[0.3066758,0.0002990976,0.6840968,0.0004987522,0.0001500024,0.0006037803,0.0008251659,0.0004850248,0.006365561],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004403513,"threshold_uncertainty_score":0.01473117,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03790433557480861,"score_gpt":0.2852573740978525,"score_spread":0.2473530385230439,"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."}}