{"id":"W4327485940","doi":"10.48550/arxiv.2303.07127","title":"Improving physics-informed neural networks with meta-learned optimization","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Model Reduction and Neural Networks","field":"Physics and Astronomy","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Artificial neural network; Differential equation; Perceptron; Burgers' equation; Computer science; Applied mathematics; Poisson's equation; Artificial intelligence; Mathematics; Mathematical optimization; Mathematical analysis","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00008893824,0.0004326277,0.0004966903,0.0001008224,0.0002202276,0.0001281674,0.0003893103,0.0001681492,0.0003227419],"category_scores_gemma":[0.000003205985,0.0004018955,0.0004110256,0.0004750787,0.0000938981,0.0003006373,0.0004532334,0.0008211201,0.00002296381],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007215635,"about_ca_system_score_gemma":0.0001137039,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003409706,"about_ca_topic_score_gemma":0.00001392,"domain_scores_codex":[0.9983743,0.00008108743,0.0002146213,0.0008119998,0.00009097521,0.000426998],"domain_scores_gemma":[0.9986438,0.00007241424,0.0003890607,0.0005908627,0.0001332431,0.0001706163],"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":[0.00007586161,0.00003614513,0.0007277627,0.00002330781,0.0007849008,0.00001445595,0.00003157805,0.9918908,0.000001068278,0.004922904,0.0002454959,0.001245735],"study_design_scores_gemma":[0.0004629568,0.00003608277,0.00002624671,0.00002233702,0.001086624,5.650058e-7,0.0001169936,0.9964896,0.00002076509,0.001267128,0.00004247752,0.0004281947],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02452714,0.00001697115,0.9729018,0.00006936493,0.0005289777,0.0004141684,0.00002434083,0.0002858091,0.001231398],"genre_scores_gemma":[0.993944,0.00003670366,0.0006976291,0.00004253209,0.0006223317,0.000007233286,0.0003130613,0.00006894163,0.004267576],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9722042,"threshold_uncertainty_score":0.9998433,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1221490669438714,"score_gpt":0.208266111818695,"score_spread":0.0861170448748236,"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."}}