{"id":"W2949509589","doi":"","title":"AntisymmetricRNN: A Dynamical System View on Recurrent Neural Networks","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Model Reduction and Neural Networks","field":"Physics and Astronomy","cited_by":41,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Recurrent neural network; Computer science; Overhead (engineering); Property (philosophy); Ordinary differential equation; Term (time); Stability (learning theory); Computation; Dynamical systems theory; Artificial neural network; Artificial intelligence; Differential (mechanical device); Dynamical system (definition); Differential equation; Theoretical computer science; Machine learning; Algorithm; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006781556,0.0006339276,0.0005087388,0.0004035006,0.0002254778,0.0006840612,0.001075649,0.0006469767,0.002392539],"category_scores_gemma":[0.00178079,0.0003559157,0.0005997422,0.0003562613,0.0007479713,0.001534965,0.0008233987,0.001191933,0.0005203075],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004483684,"about_ca_system_score_gemma":0.0003999256,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001617341,"about_ca_topic_score_gemma":0.00189792,"domain_scores_codex":[0.999675,0.0001076891,0.00002221765,0.00009434416,0.00007775362,0.0000230682],"domain_scores_gemma":[0.9996051,0.0001555368,0.00006588385,0.00007368332,0.00008045459,0.00001938769],"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":[0.00006491222,0.00004069556,0.001081303,0.0002384727,0.00009582752,0.0002525975,0.0001529228,0.5410261,0.01739222,0.3798922,0.003184288,0.05657835],"study_design_scores_gemma":[0.000004710485,0.00002346521,0.0001493847,0.000008023005,0.00001031445,0.00004875794,0.000006833724,0.9271173,0.001079189,0.06902363,0.002520281,0.000008063737],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01257006,0.0004468912,0.9814845,0.0002999375,0.00007620837,0.00002497945,0.0001896874,0.0002943385,0.004613371],"genre_scores_gemma":[0.6369305,0.001968291,0.3489026,0.0004259278,0.0002956017,0.0002322853,0.0007589621,0.0002730716,0.01021289],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002392539,"threshold_uncertainty_score":0.008003831,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05251788679225956,"score_gpt":0.1956624532481049,"score_spread":0.1431445664558453,"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."}}