{"id":"W4387023498","doi":"10.1002/nme.7357","title":"Transfer learning of recurrent neural network‐based plasticity models","year":2023,"lang":"en","type":"article","venue":"International Journal for Numerical Methods in Engineering","topic":"Non-Destructive Testing Techniques","field":"Engineering","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Initialization; Generalization; Transfer of learning; Convergence (economics); Computer science; Artificial neural network; Artificial intelligence; Stress (linguistics); Stress space; Plasticity; Transfer (computing); Machine learning; Ensemble learning; Space (punctuation); Algorithm; Mathematics; Finite element method; Structural engineering; Materials science; Engineering; Mathematical analysis","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":[0.001149277,0.000707839,0.0006651303,0.0004261674,0.0001654189,0.0005400062,0.001174385,0.0009248965,0.001442529],"category_scores_gemma":[0.002897048,0.0003624817,0.000721982,0.000317705,0.0004885168,0.0009341171,0.0007287862,0.0009998454,0.0003908763],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005333247,"about_ca_system_score_gemma":0.0003740801,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003410621,"about_ca_topic_score_gemma":0.002729272,"domain_scores_codex":[0.9997092,0.000120745,0.00001451012,0.00006362589,0.00005714691,0.00003465151],"domain_scores_gemma":[0.9990861,0.000517485,0.0001031762,0.00009548996,0.0001658426,0.00003194632],"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":[0.00002175761,0.00002403016,0.0002182824,0.00001358031,0.00002091591,0.00002273212,0.00001349687,0.983649,0.0009026516,0.001145679,0.0001806814,0.01378728],"study_design_scores_gemma":[4.512063e-7,0.000004293175,0.00001836249,6.27847e-7,7.448157e-7,0.000001237718,5.089127e-7,0.9995962,0.0001103236,0.0002485076,0.00001790846,7.948926e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1848435,0.0005074472,0.8088448,0.0003239265,0.00007958218,0.00005212014,0.0001217617,0.001091923,0.00413495],"genre_scores_gemma":[0.9689463,0.0001184696,0.02782694,0.00005742738,0.00002286986,0.00007064368,0.0001367995,0.00005423696,0.002766342],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003410621,"threshold_uncertainty_score":0.006781518,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05914358742517486,"score_gpt":0.3773666423825993,"score_spread":0.3182230549574244,"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."}}