{"id":"W4298625139","doi":"10.1007/s00521-022-07785-2","title":"Convolutional neural networks combined with Runge–Kutta methods","year":2022,"lang":"en","type":"article","venue":"Neural Computing and Applications","topic":"Model Reduction and Neural Networks","field":"Physics and Astronomy","cited_by":30,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"Fundamental Research Funds for the Central Universities","keywords":"Runge–Kutta methods; Computer science; Dynamical systems theory; Benchmark (surveying); Dynamical system (definition); Artificial neural network; Convolutional neural network; Residual; Applied mathematics; Trajectory; Recurrent neural network; Inference; Computational Science and Engineering; Algorithm; Artificial intelligence; Numerical analysis; Machine learning; Mathematics","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":[0.0001455592,0.00015213,0.000163537,0.00003944105,0.001134092,0.00005467356,0.0001543454,0.00001776228,0.000175513],"category_scores_gemma":[5.860974e-7,0.0001388031,0.00005599809,0.000295502,0.00008657385,0.00004841982,0.0001722098,0.000428691,0.000001411371],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001461938,"about_ca_system_score_gemma":0.0000159415,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002801201,"about_ca_topic_score_gemma":4.808442e-7,"domain_scores_codex":[0.9989429,0.000144982,0.0001936118,0.000336359,0.0001311097,0.0002510829],"domain_scores_gemma":[0.999409,0.0001394845,0.0001116219,0.0001917989,0.00004013258,0.0001079168],"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":[0.00007811072,0.0001766117,0.00796825,0.000006255073,0.00005797822,8.676349e-7,0.00008340005,0.6892492,0.0001900682,0.08005275,0.001901028,0.2202355],"study_design_scores_gemma":[0.0004465811,0.0001076108,0.001452672,0.000002120844,0.00002499938,0.00002131257,0.0001463044,0.9869477,0.00002064446,0.001210185,0.009438154,0.0001816847],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2640076,0.0002612341,0.7309958,0.001359998,0.0002675416,0.0006765396,0.00002835895,0.0002006997,0.002202242],"genre_scores_gemma":[0.9959357,0.000001290472,0.002694955,0.0003002629,0.0004798342,0.000168805,0.0001114959,0.00001822673,0.0002894075],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7319281,"threshold_uncertainty_score":0.8722631,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01685992339212256,"score_gpt":0.2960431966861271,"score_spread":0.2791832732940046,"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."}}