{"id":"W4416863416","doi":"10.23977/jeis.2025.100217","title":"A Comparative Study on the Training Effects of Different Optimizers for Deep Learning Models","year":2025,"lang":"","type":"article","venue":"Journal of Electronics and Information Science","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Convergence (economics); Artificial neural network; Stochastic gradient descent; Deep learning; Generalization; Selection (genetic algorithm); Overfitting; Moment (physics); Training (meteorology)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003640529,0.0001602824,0.0003771918,0.0005862592,0.000752707,0.0005919585,0.0009072771,0.00003807207,8.97499e-7],"category_scores_gemma":[0.0009320609,0.000100784,0.00008590939,0.001013023,0.0002272799,0.004200053,0.0001277794,0.0005739315,3.760613e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001261505,"about_ca_system_score_gemma":0.0006709266,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002007368,"about_ca_topic_score_gemma":9.087466e-7,"domain_scores_codex":[0.9977916,0.0001929847,0.0008581096,0.000162998,0.0006806278,0.0003136143],"domain_scores_gemma":[0.9963353,0.001122394,0.001407245,0.0002443285,0.0008113928,0.00007929236],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002898033,0.0003374456,0.0002656958,0.0001470086,0.0001228268,2.76758e-7,0.09385411,0.115327,0.001318315,0.6076136,0.00005579013,0.1806682],"study_design_scores_gemma":[0.001056292,0.003152032,0.004094254,0.0001752783,0.00004690353,0.000004268198,0.006125055,0.9816537,0.001078867,0.002050218,0.0004683723,0.00009468451],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2832018,0.000412279,0.7136391,0.001000013,0.0002638802,0.0005446719,6.862396e-7,0.000005122035,0.0009324267],"genre_scores_gemma":[0.9982758,0.0004231235,0.001088202,0.0001679986,0.00001453083,0.00001135461,7.019197e-7,0.000001790955,0.00001646424],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8663268,"threshold_uncertainty_score":0.5789289,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03823319963320846,"score_gpt":0.3136478977489772,"score_spread":0.2754146981157687,"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."}}