{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002342533,0.001395864,0.001097873,0.0008159058,0.000620939,0.001030529,0.002060886,0.001286786,0.00304352],"category_scores_gemma":[0.006554021,0.000566763,0.0005843571,0.001275451,0.0006031044,0.001833201,0.002112471,0.002529258,0.001074391],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006079942,"about_ca_system_score_gemma":0.0008776205,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001841893,"about_ca_topic_score_gemma":0.004541013,"domain_scores_codex":[0.9992206,0.0002116417,0.00007412599,0.0001388487,0.0002659634,0.00008885488],"domain_scores_gemma":[0.9981791,0.0006852484,0.0001072468,0.0003578917,0.0005764185,0.00009413993],"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":[0.0003470782,0.0003228464,0.001709505,0.0001174023,0.000155765,0.0001675068,0.0001381294,0.116908,0.02334029,0.01796361,0.01149724,0.8273327],"study_design_scores_gemma":[0.0000299714,0.00006165411,0.0003256462,0.000020333,0.00003566786,0.00005744976,0.00002427505,0.9787291,0.004906583,0.01444203,0.001357276,0.00001001419],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0186462,0.0005330649,0.9775367,0.0003485288,0.0002126654,0.00008621103,0.00007028265,0.0006977452,0.001868634],"genre_scores_gemma":[0.36802,0.0006463373,0.6187212,0.0005141899,0.0004152734,0.0003387821,0.000591689,0.0003695086,0.0103831],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00304352,"threshold_uncertainty_score":0.01238865,"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."}}