{"id":"W4287064118","doi":"10.48550/arxiv.2107.14194","title":"On the combined effect of class imbalance and concept complexity in deep\\n learning","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada; University of Alberta","funders":"","keywords":"Artificial intelligence; Overfitting; MNIST database; Machine learning; Deep learning; Computer science; Class (philosophy); Scarcity; Simple (philosophy); Artificial neural network; Economics","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":[0.009539037,0.0007903459,0.0008281249,0.0009324877,0.001070066,0.002540378,0.0009264258,0.001245169,0.002329007],"category_scores_gemma":[0.0384743,0.00042627,0.00049423,0.0009514432,0.002081946,0.006702174,0.002609821,0.003573016,0.0005752956],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001729073,"about_ca_system_score_gemma":0.0009789799,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003200826,"about_ca_topic_score_gemma":0.004331214,"domain_scores_codex":[0.9974141,0.0007575355,0.0001360781,0.0005935259,0.0008446198,0.0002541005],"domain_scores_gemma":[0.9770728,0.01698619,0.001978536,0.001845826,0.001371152,0.0007453518],"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":[0.002222253,0.0005922781,0.08364019,0.0006746313,0.0004452631,0.0006149622,0.002164578,0.4736433,0.01772559,0.06169631,0.01174389,0.3448368],"study_design_scores_gemma":[0.00005361473,0.0005416317,0.01989324,0.0001794428,0.00007585488,0.0003325522,0.0004938811,0.8361588,0.01430429,0.1238869,0.00400947,0.00007026223],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7348877,0.004931854,0.2349256,0.007752372,0.0003228737,0.0001596501,0.0005733349,0.0008661933,0.01558028],"genre_scores_gemma":[0.9813157,0.0007079035,0.0148299,0.0005498073,0.0001123674,0.00004609727,0.0002875178,0.00007038083,0.002080347],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009539037,"threshold_uncertainty_score":0.05044788,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05920185141972074,"score_gpt":0.2093491840486144,"score_spread":0.1501473326288937,"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."}}