{"id":"W4313421210","doi":"10.1007/s10994-022-06268-8","title":"The class imbalance problem in deep learning","year":2022,"lang":"en","type":"article","venue":"Machine Learning","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":270,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa; National Research Council Canada; University of Alberta","funders":"","keywords":"Artificial intelligence; Deep learning; Computer science; Machine learning; Class (philosophy); Context (archaeology)","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":[0.01449408,0.0009669418,0.002227949,0.001564289,0.00149222,0.003510124,0.00257859,0.00284794,0.001777309],"category_scores_gemma":[0.04942196,0.001052977,0.0009166725,0.002789885,0.003069341,0.008102885,0.003722457,0.007128584,0.0004575509],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002133526,"about_ca_system_score_gemma":0.00204153,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002037261,"about_ca_topic_score_gemma":0.002117167,"domain_scores_codex":[0.991567,0.003327344,0.0004755483,0.001490694,0.002700034,0.0004394547],"domain_scores_gemma":[0.9776968,0.01551331,0.001723481,0.002497587,0.00216492,0.0004039591],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0005641942,0.0003346279,0.01250762,0.0006879725,0.0002931908,0.0003736926,0.000603973,0.1315224,0.002620684,0.2685615,0.03197213,0.5499581],"study_design_scores_gemma":[0.00003842068,0.00006743457,0.001607836,0.0001078531,0.00004604247,0.0002016005,0.0001108795,0.5631695,0.00264576,0.4250232,0.006953498,0.00002799139],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.02149487,0.003525169,0.9677591,0.004074173,0.0005334838,0.00006431165,0.0002595072,0.0003401246,0.001949238],"genre_scores_gemma":[0.6581174,0.004847474,0.3212494,0.002541717,0.002495955,0.0005685629,0.001091097,0.0003698313,0.008718563],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.01449408,"threshold_uncertainty_score":0.07665294,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007893058798280584,"score_gpt":0.2351205030355744,"score_spread":0.2272274442372938,"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."}}