{"id":"W3107092601","doi":"10.1109/access.2020.3041873","title":"DCBT-Net: Training Deep Convolutional Neural Networks With Extremely Noisy Labels","year":2020,"lang":"en","type":"article","venue":"IEEE Access","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Ministry of Science and ICT, South Korea; National Research Foundation of Korea; National IT Industry Promotion Agency; Kyungpook National University; National Research Foundation","keywords":"Computer science; Convolutional neural network; Artificial intelligence; Training (meteorology); Net (polyhedron); Machine learning; Pattern recognition (psychology); Speech recognition; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001450839,0.0001424698,0.0001471984,0.00004006355,0.0001680873,0.0004261817,0.001263544,0.00005169461,0.00003581654],"category_scores_gemma":[0.00004249174,0.0001204393,0.00003097219,0.0004595799,0.00005084168,0.00103094,0.0001330988,0.0002787229,0.00002783172],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001723364,"about_ca_system_score_gemma":0.00005259076,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004430736,"about_ca_topic_score_gemma":0.00003118893,"domain_scores_codex":[0.9987074,0.00008416126,0.0001851664,0.000456344,0.0002882654,0.0002786419],"domain_scores_gemma":[0.9992027,0.0001001362,0.0001300389,0.0003323124,0.00007195342,0.0001628526],"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":[0.0001333401,0.0001237978,0.08530978,0.00006390764,0.0001016519,0.0001197175,0.004284986,0.494952,0.001078715,0.02377226,0.007883188,0.3821766],"study_design_scores_gemma":[0.0003499406,0.00006148368,0.03574802,0.000009098369,0.000006703596,0.00001463919,0.00001672814,0.9606174,0.00004219247,0.00008355623,0.002875365,0.0001748862],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02350992,0.0001499315,0.9695768,0.005060541,0.0002747939,0.0001032017,0.000003871618,0.0002795683,0.001041368],"genre_scores_gemma":[0.9908653,0.000004966514,0.006034803,0.002597874,0.0003952531,0.00001468439,0.0000290038,0.00001265657,0.00004540491],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9673554,"threshold_uncertainty_score":0.4911372,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07748383957779421,"score_gpt":0.287544198648785,"score_spread":0.2100603590709908,"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."}}