{"id":"W2915445509","doi":"10.4018/ijssci.2018100102","title":"Preventing Model Overfitting and Underfitting in Convolutional Neural Networks","year":2018,"lang":"en","type":"article","venue":"International Journal of Software Science and Computational Intelligence","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":98,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Overfitting; Computer science; Artificial intelligence; Convolutional neural network; Regularization (linguistics); Machine learning; Adaptability; Deep learning; Pattern recognition (psychology); Set (abstract data type); Artificial neural network","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":[0.008505819,0.00147911,0.001805276,0.001269221,0.0008426504,0.001626324,0.001848572,0.001774331,0.0008948339],"category_scores_gemma":[0.05212159,0.001081747,0.001279663,0.0008504834,0.002232523,0.003054407,0.002877645,0.003228891,0.0002373552],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00139074,"about_ca_system_score_gemma":0.002110155,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003912392,"about_ca_topic_score_gemma":0.005189976,"domain_scores_codex":[0.9963223,0.00152656,0.0003279982,0.0005060279,0.001062132,0.0002549351],"domain_scores_gemma":[0.9800763,0.01366784,0.00171884,0.002612917,0.001681043,0.0002430948],"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":[0.0002034786,0.00009874041,0.006140885,0.0003500004,0.0002584709,0.0003572339,0.0003032111,0.8616459,0.006786031,0.02928686,0.001885687,0.09268352],"study_design_scores_gemma":[0.000007963242,0.0000506619,0.0003863312,0.00004280742,0.0000265474,0.00006385305,0.00002386878,0.9763179,0.003708964,0.01887208,0.0004858791,0.00001332367],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0677589,0.0009260911,0.9277732,0.0008236433,0.00007805006,0.0000612713,0.00004916231,0.001178475,0.001351143],"genre_scores_gemma":[0.8071842,0.0009980561,0.1885038,0.0006511462,0.00006999999,0.0002299703,0.0002708687,0.0005368256,0.001555268],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008505819,"threshold_uncertainty_score":0.04498363,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02465964199239385,"score_gpt":0.3058860702326626,"score_spread":0.2812264282402688,"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."}}