{"id":"W4401503623","doi":"10.1016/j.ins.2024.121317","title":"An analytic formulation of convolutional neural network learning for pattern recognition","year":2024,"lang":"en","type":"article","venue":"Information Sciences","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University","funders":"Ministry of Education, Science and Technology; National Research Foundation of Korea; National Natural Science Foundation of China","keywords":"MNIST database; Computer science; Interpretability; Convolutional neural network; Artificial intelligence; Machine learning; Overfitting; Benchmark (surveying); Artificial neural network; Regularization (linguistics); Deep learning; Perceptron; Pattern recognition (psychology)","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005117602,0.00005631461,0.00006309819,0.0001168758,0.0002627944,0.0003644064,0.0002776336,0.00002559487,0.000009752081],"category_scores_gemma":[0.0000174208,0.00004720221,0.00004362633,0.0007011816,0.00004688796,0.004318755,0.00002596054,0.00005477764,0.00001892738],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001362442,"about_ca_system_score_gemma":0.00005046884,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001282745,"about_ca_topic_score_gemma":0.000004364007,"domain_scores_codex":[0.9992176,0.00001937563,0.0002780215,0.0001227914,0.000216701,0.0001455277],"domain_scores_gemma":[0.999494,0.0001494101,0.00011141,0.00008799684,0.0001223239,0.00003484952],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001885705,0.000007116988,0.0006933108,0.00002862277,0.000004282342,6.440528e-8,0.0003733469,0.3061572,0.00007907375,0.0340149,0.0006558547,0.6579843],"study_design_scores_gemma":[0.0000508663,0.00009119646,0.002757118,0.00002145519,0.000003330371,0.00000354475,0.0000343197,0.9845753,0.00008445208,0.00958958,0.002725096,0.00006371774],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04856971,0.00003917641,0.9499305,0.000533516,0.0002541446,0.0001752427,0.000005623227,0.000115211,0.0003768169],"genre_scores_gemma":[0.991756,0.000005290262,0.007872375,0.0001686326,0.0001048547,0.00003011783,0.0000539688,0.000001443249,0.000007290684],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9431863,"threshold_uncertainty_score":0.351398,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0448100433585641,"score_gpt":0.3101929272162299,"score_spread":0.2653828838576658,"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."}}