{"id":"W3094623068","doi":"","title":"How to Train Your Neural ODE: the World of Jacobian and Kinetic Regularization","year":2020,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Model Reduction and Neural Networks","field":"Physics and Astronomy","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; McGill University","funders":"","keywords":"Ode; Solver; Regularization (linguistics); Jacobian matrix and determinant; Artificial neural network; Computer science; Convergence (economics); Applied mathematics; Stability (learning theory); Mathematical optimization; Mathematics; Artificial intelligence; Machine learning","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":[0.00005086992,0.00008706253,0.00008823979,0.00004502981,0.00006039993,0.0000987322,0.0001407917,0.00001193107,0.0004507898],"category_scores_gemma":[0.00002228373,0.00006602163,0.00003437555,0.0001081791,0.00002690324,0.0000653748,0.00004356242,0.0002515499,0.000004127026],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004420895,"about_ca_system_score_gemma":0.000008553085,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003013501,"about_ca_topic_score_gemma":0.000006092394,"domain_scores_codex":[0.9994333,0.00005900542,0.0001126066,0.0001600331,0.0001531671,0.00008188762],"domain_scores_gemma":[0.9997095,0.00002855487,0.0000826944,0.00005405085,0.00006151501,0.00006363544],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002307986,0.00005859771,0.02610357,0.00001311939,0.0001023806,0.000002138006,0.002088576,0.09121322,0.02498133,0.6189829,0.0007916134,0.2354318],"study_design_scores_gemma":[0.0003137943,0.000111518,0.003423053,0.00002775728,0.000009441755,0.000001014531,0.0003173393,0.9831844,0.0009822545,0.00136596,0.01014689,0.000116603],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6108937,0.00003529651,0.09373313,0.2512605,0.0004826114,0.0004500046,0.0000433303,0.00007631008,0.04302514],"genre_scores_gemma":[0.9946931,0.000002017126,0.0001545535,0.0005115786,0.0002743431,0.000006020972,0.0000340335,0.000008325726,0.004316028],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8919712,"threshold_uncertainty_score":0.4935831,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04947007862184124,"score_gpt":0.2891593166532649,"score_spread":0.2396892380314237,"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."}}