{"id":"W2619846146","doi":"10.1007/978-3-319-59876-5_1","title":"A Weight-Selection Strategy on Training Deep Neural Networks for Imbalanced Classification","year":2017,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; MNIST database; Artificial intelligence; Artificial neural network; Selection (genetic algorithm); Machine learning; Set (abstract data type); Class (philosophy); Deep neural networks; Training (meteorology); Pattern recognition (psychology)","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001010105,0.000611368,0.0005798971,0.0007486211,0.0006574994,0.001181151,0.004299841,0.0005329258,0.000006892866],"category_scores_gemma":[0.0001845564,0.0005865736,0.0001636495,0.0002985234,0.0005370836,0.001119555,0.0003790151,0.000953084,0.00001005547],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004905261,"about_ca_system_score_gemma":0.0003643358,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006744086,"about_ca_topic_score_gemma":0.0000640865,"domain_scores_codex":[0.9957001,0.00004659729,0.0006437356,0.002048616,0.0007398483,0.0008210698],"domain_scores_gemma":[0.9959105,0.0005103011,0.0008657832,0.00214133,0.0004068658,0.0001651666],"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":[0.00001799948,0.00002165255,0.00002004375,0.00001731561,0.000008069293,0.000004939066,0.0001603727,0.03407573,0.0003052421,0.07144529,0.00004823459,0.8938751],"study_design_scores_gemma":[0.0002851235,0.0003452954,0.0005076826,0.0001472305,0.000007239122,0.00002605116,1.867973e-7,0.9177796,0.0008474314,0.0783672,0.001114105,0.0005728385],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00001201225,0.00008765568,0.9935656,0.0008137551,0.001513888,0.0009836827,0.00001187224,0.000504927,0.002506588],"genre_scores_gemma":[0.631292,0.00005128144,0.3659946,0.0009727548,0.001079993,0.0001659234,0.00007411533,0.0000663772,0.00030287],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8933023,"threshold_uncertainty_score":0.9998557,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05085676056954021,"score_gpt":0.2947353926549329,"score_spread":0.2438786320853927,"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."}}