{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004622273,0.001683681,0.001125687,0.0008852097,0.0005176977,0.0009427408,0.0007915357,0.001244218,0.0007424799],"category_scores_gemma":[0.01283724,0.0005067644,0.0007926679,0.0007118626,0.0007341785,0.001930846,0.0008484517,0.001510979,0.0002204005],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007690441,"about_ca_system_score_gemma":0.0009676504,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006054861,"about_ca_topic_score_gemma":0.00594361,"domain_scores_codex":[0.9988165,0.00046491,0.0001395422,0.0002127638,0.0002333754,0.0001329249],"domain_scores_gemma":[0.9954931,0.002950112,0.0002976523,0.00047476,0.0006685555,0.0001157853],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006229948,0.0002884544,0.006949986,0.0004639189,0.0002619358,0.0001410859,0.0001466739,0.8732964,0.006021195,0.003699028,0.001791695,0.1063165],"study_design_scores_gemma":[0.00002693604,0.0003166278,0.001923167,0.00004434645,0.00006123084,0.00003693279,0.00004317646,0.9893112,0.006992436,0.0007904758,0.0004328458,0.00002061255],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7337679,0.007711102,0.2458262,0.0008227726,0.0002387922,0.0002083116,0.0003780073,0.002240407,0.008806507],"genre_scores_gemma":[0.9448858,0.001481625,0.05158561,0.0001178112,0.00003286736,0.0001333135,0.0004758541,0.0002681403,0.001018982],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006054861,"threshold_uncertainty_score":0.02444518,"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."}}