{"id":"W2825245636","doi":"10.1109/tnnls.2019.2899649","title":"Reservoir Computing Universality With Stochastic Inputs","year":2019,"lang":"en","type":"preprint","venue":"IEEE Transactions on Neural Networks and Learning Systems","topic":"Neural Networks and Reservoir Computing","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Universität St. Gallen; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; Agence Nationale de la Recherche; Ottawa Hospital Research Institute; National Science Foundation","keywords":"Universality (dynamical systems); Reservoir computing; Affine transformation; Computer science; Artificial neural network; Trigonometry; Linearity; Property (philosophy); Mathematics; Applied mathematics; Theoretical computer science; Artificial intelligence; Recurrent neural network; Pure mathematics; 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","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0007296256,0.0006914603,0.000859718,0.0002601904,0.001020499,0.001079792,0.001088225,0.000468749,0.000002525604],"category_scores_gemma":[0.000006176118,0.0005622484,0.0002094393,0.0005453119,0.0001190486,0.0002858009,0.0001101903,0.004631195,0.000006201123],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001115822,"about_ca_system_score_gemma":0.00008805223,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003391148,"about_ca_topic_score_gemma":0.00002480202,"domain_scores_codex":[0.9955498,0.0009868353,0.0006135823,0.001432088,0.0005927485,0.0008249514],"domain_scores_gemma":[0.9971582,0.0008354786,0.000556847,0.0009766925,0.0001882834,0.0002844489],"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":[0.00005617744,0.00004279797,0.0000751774,0.0002079724,0.0001110568,0.00005213214,0.0002483698,0.9929386,0.000003291601,0.00007033422,0.00006586401,0.006128192],"study_design_scores_gemma":[0.0005212864,0.0004215462,0.0001151758,0.001298947,0.00004847893,0.0001219898,0.00007262437,0.9965641,0.000002974478,0.000009243938,0.0001745202,0.0006491182],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1039305,0.0006376514,0.8893649,0.0003729222,0.004245826,0.0007883449,0.000003375171,0.0005705899,0.00008585316],"genre_scores_gemma":[0.9979057,0.00005868459,0.0006392423,0.0001235259,0.000495852,0.00001661103,0.00000687637,0.00006908614,0.0006844676],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8939751,"threshold_uncertainty_score":0.9999572,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01631229409661925,"score_gpt":0.2303646946748719,"score_spread":0.2140524005782527,"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."}}