{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003937666,0.00008200039,0.0003496699,0.00009949392,0.0000700007,0.00002917284,0.0003823581,0.00003379567,0.00001121279],"category_scores_gemma":[0.0001854832,0.00005552123,0.00007801422,0.0008967991,0.0002733758,0.0001454545,0.00009278618,0.0001940226,6.973158e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001239712,"about_ca_system_score_gemma":0.0000827085,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002921921,"about_ca_topic_score_gemma":0.000001803252,"domain_scores_codex":[0.9988042,0.0001412997,0.0005820714,0.0001341709,0.0002027882,0.0001355431],"domain_scores_gemma":[0.9980364,0.0009304143,0.0005389756,0.0001741849,0.0002438998,0.00007609375],"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":[0.0004735063,0.0006518998,0.3190047,0.0001662571,0.001118616,0.00001549001,0.0004261656,0.1209097,0.02652134,0.5041267,0.00788545,0.01870013],"study_design_scores_gemma":[0.0003006971,0.0001552335,0.3583838,0.0001035095,0.0001671753,0.000002437577,0.00001785683,0.6324993,0.0006772294,0.007557676,0.00007618065,0.00005894481],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4526748,0.0001937025,0.5467449,0.0001710564,0.00009552234,0.00004241963,0.00004075417,0.000002376268,0.00003448351],"genre_scores_gemma":[0.9895495,0.00004775538,0.01028273,0.00008764989,0.00001057698,9.04412e-7,0.000004156486,0.000001501931,0.00001526351],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5368747,"threshold_uncertainty_score":0.226409,"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."}}