{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007131154,0.0006426433,0.0004627103,0.000698757,0.0003172919,0.001137331,0.001077401,0.0009146786,0.003941314],"category_scores_gemma":[0.002863832,0.0003145678,0.000540779,0.000695364,0.0009538393,0.001942708,0.000782426,0.001273206,0.0007129014],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001168711,"about_ca_system_score_gemma":0.0009239193,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003405952,"about_ca_topic_score_gemma":0.003435677,"domain_scores_codex":[0.9997887,0.00006237166,0.00001197973,0.0000346542,0.00007985267,0.0000223494],"domain_scores_gemma":[0.9995368,0.0002151905,0.00005027539,0.00003751796,0.0001356751,0.00002455157],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000007923099,0.0000118517,0.0001317854,0.00008576791,0.00001419015,0.00004585129,0.00004678604,0.07595325,0.001663894,0.9017956,0.002831283,0.01741184],"study_design_scores_gemma":[0.00000200713,0.000007167233,0.00007727195,0.00001487159,0.000004259546,0.00003362614,0.00001045914,0.6319337,0.000232417,0.3645451,0.003133654,0.000005392485],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004059533,0.001222938,0.9832606,0.001111295,0.0001348572,0.00002004307,0.0001163444,0.00007962662,0.009994691],"genre_scores_gemma":[0.5459448,0.006056459,0.3907609,0.001353275,0.001106378,0.0002488781,0.0004645267,0.0003088819,0.05375593],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003941314,"threshold_uncertainty_score":0.01318502,"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."}}