{"id":"W3037447448","doi":"10.3389/fams.2022.818799","title":"On Lyapunov Exponents for RNNs: Understanding Information Propagation Using Dynamical Systems Tools","year":2022,"lang":"en","type":"article","venue":"Frontiers in Applied Mathematics and Statistics","topic":"Neural dynamics and brain function","field":"Neuroscience","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"Natural Sciences and Engineering Research Council of Canada; Institut de Valorisation des Données; Fonds de recherche du Québec – Nature et technologies; University of Washington; Canadian Institute for Advanced Research; Netherlands eScience Center; Washington Research Foundation; National Science Foundation","keywords":"Recurrent neural network; Computer science; Dynamical systems theory; Attractor; Lyapunov exponent; Lyapunov function; Initialization; Hyperparameter; Leverage (statistics); Artificial intelligence; Mathematics; Artificial neural network; Chaotic; Nonlinear system","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001781235,0.001232731,0.0006612385,0.001840579,0.0004350962,0.001575867,0.0008655966,0.0008877242,0.00278541],"category_scores_gemma":[0.01082075,0.0004741369,0.0008361257,0.0006532883,0.001564597,0.003148636,0.001414525,0.002042866,0.0005764109],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008394279,"about_ca_system_score_gemma":0.0005453229,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002183327,"about_ca_topic_score_gemma":0.001574387,"domain_scores_codex":[0.9995387,0.0001796383,0.00004472455,0.00008430727,0.0001153679,0.00003733792],"domain_scores_gemma":[0.9965715,0.0025071,0.0003140875,0.0001819318,0.000329369,0.00009604593],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002362061,0.00002175352,0.001316394,0.0001494357,0.00003824863,0.0001723099,0.0003288279,0.4534099,0.003381023,0.5166711,0.001141968,0.02334529],"study_design_scores_gemma":[0.000002913496,0.00001298403,0.0001772162,0.00003048594,0.000003988092,0.00001802048,0.00001963891,0.7966508,0.0003506089,0.2018426,0.0008800649,0.00001081294],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01269118,0.0009273404,0.9832051,0.0003764871,0.00005472547,0.00002557513,0.00008601599,0.0001283339,0.002505263],"genre_scores_gemma":[0.7194531,0.005032324,0.2670829,0.0003562493,0.0005694922,0.0004157547,0.0004268188,0.0004289947,0.006234338],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00278541,"threshold_uncertainty_score":0.009420216,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06218042407756191,"score_gpt":0.2571484869486104,"score_spread":0.1949680628710485,"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."}}