{"id":"W4408591874","doi":"10.1016/j.jspi.2025.106291","title":"Analysis of the rate of convergence of an over-parametrized convolutional neural network image classifier learned by gradient descent","year":2025,"lang":"en","type":"article","venue":"Journal of Statistical Planning and Inference","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Deutsche Forschungsgemeinschaft","keywords":"Mathematics; Gradient descent; Rate of convergence; Classifier (UML); Convolutional neural network; Stochastic gradient descent; Artificial intelligence; Pattern recognition (psychology); Convergence (economics); Artificial neural network; Applied mathematics; Computer science","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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":[0.007635107,0.0009242328,0.001099028,0.0008689185,0.0006160021,0.001277365,0.001606795,0.001954057,0.002275105],"category_scores_gemma":[0.05817081,0.0005895733,0.0006013912,0.0006861545,0.00123724,0.002291261,0.001363514,0.002289623,0.0004141657],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002051132,"about_ca_system_score_gemma":0.001831058,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008562531,"about_ca_topic_score_gemma":0.00539995,"domain_scores_codex":[0.9984622,0.0006304416,0.00008968714,0.0003007645,0.0003661469,0.0001507269],"domain_scores_gemma":[0.9565279,0.03608501,0.001485358,0.001967355,0.003397055,0.0005373738],"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":[0.001508255,0.0001533374,0.01169801,0.0003087196,0.0002268474,0.0002537393,0.0001809722,0.889227,0.01037256,0.01557334,0.002876887,0.06762027],"study_design_scores_gemma":[0.000008806641,0.00004276106,0.0008256884,0.00001012414,0.00001137269,0.00003836833,0.00001204003,0.996161,0.001695749,0.001083203,0.0001034368,0.000007445926],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5133089,0.002605285,0.4760463,0.001502832,0.0001860182,0.0001407203,0.000530814,0.001859574,0.003819554],"genre_scores_gemma":[0.9352433,0.0004197321,0.05945097,0.0001631042,0.00005538506,0.0001102322,0.0008484427,0.0006226852,0.003086067],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008562531,"threshold_uncertainty_score":0.04037875,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02429904016378327,"score_gpt":0.3194354658497086,"score_spread":0.2951364256859253,"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."}}