{"id":"W4391386721","doi":"10.3390/e26020129","title":"Deep Individual Active Learning: Safeguarding against Out-of-Distribution Challenges in Neural Networks","year":2024,"lang":"en","type":"article","venue":"Entropy","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institute for Advanced Research","keywords":"MNIST database; Computer science; Leverage (statistics); Regret; Machine learning; Artificial intelligence; Artificial neural network; Key (lock); Test set; Set (abstract data type); Training set; Active learning (machine learning); Data mining","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008491765,0.001855936,0.002632301,0.0009182784,0.001207907,0.002307401,0.005633494,0.002725133,0.001497564],"category_scores_gemma":[0.01898433,0.001024016,0.001005117,0.001121588,0.002941634,0.005484763,0.005981518,0.005626238,0.0005643742],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001688518,"about_ca_system_score_gemma":0.002136986,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00227419,"about_ca_topic_score_gemma":0.003679273,"domain_scores_codex":[0.9967638,0.001529807,0.0001463997,0.0005330534,0.000728846,0.0002980549],"domain_scores_gemma":[0.9879547,0.007887872,0.0007793169,0.001964289,0.00104513,0.0003686771],"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":[0.0008067113,0.0003835573,0.003250454,0.0002187226,0.0002155873,0.0002388477,0.0003778546,0.6800259,0.005161699,0.04351461,0.006916919,0.2588891],"study_design_scores_gemma":[0.0000185325,0.00004458454,0.00006193488,0.0000114652,0.000009833363,0.00002437606,0.00001423018,0.9789075,0.001323723,0.01917628,0.000401727,0.000005750533],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02184369,0.0007498187,0.9743078,0.000805631,0.00007964361,0.00005635994,0.00007589217,0.0007920963,0.001289126],"genre_scores_gemma":[0.8047637,0.0006949849,0.1877836,0.00109378,0.0002926176,0.0003552138,0.0004148919,0.0003131827,0.004288067],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008491765,"threshold_uncertainty_score":0.0449093,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02338040948801737,"score_gpt":0.2668676243540459,"score_spread":0.2434872148660286,"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."}}