{"id":"W2911982542","doi":"10.48550/arxiv.1902.06094","title":"Differentiable reservoir computing","year":2019,"lang":"en","type":"preprint","venue":"Alexandria (UniSG) (University of St.Gallen)","topic":"Neural Networks and Reservoir Computing","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Universität Konstanz; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; Agence Nationale de la Recherche; Ottawa Hospital Research Institute; National Science Foundation","keywords":"Reservoir computing; Corollary; Attractor; Differentiable function; Filter (signal processing); Series (stratigraphy); Volterra series; Chaotic; Representation (politics); Dynamical systems theory; Taylor series; Computer science; State (computer science); Applied mathematics; Mathematics; Pure mathematics; Artificial neural network; Recurrent neural network; Algorithm; Mathematical analysis; Artificial intelligence","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","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0005483055,0.0005979647,0.001111247,0.0004545759,0.0006714816,0.0002622223,0.005490118,0.0006044068,0.0002207757],"category_scores_gemma":[0.00002186628,0.0006914957,0.0005932191,0.000604551,0.0002156878,0.0006841649,0.01259284,0.001445161,0.0001055796],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001321085,"about_ca_system_score_gemma":0.0003107061,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007206827,"about_ca_topic_score_gemma":0.0001899314,"domain_scores_codex":[0.995936,0.0003081367,0.0004485566,0.001522948,0.0008869922,0.0008973111],"domain_scores_gemma":[0.9958882,0.0003518822,0.0008597594,0.002217883,0.000386324,0.0002960055],"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":[0.0004586776,0.001803644,0.01234754,0.0057235,0.003328676,0.001422669,0.01331937,0.6227704,0.00129631,0.1116568,0.1758689,0.05000357],"study_design_scores_gemma":[0.00181149,0.0002392213,0.009381662,0.001402955,0.000114112,0.0000267112,0.0006572693,0.9617069,0.00004706665,0.005842117,0.017495,0.001275469],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5550385,0.001315368,0.4244792,0.003298633,0.002892047,0.0009252024,0.00005143478,0.0005355625,0.01146414],"genre_scores_gemma":[0.951115,0.000598708,0.03985996,0.0001002672,0.0003020271,4.198259e-7,0.0000920003,0.00004864427,0.00788301],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3960765,"threshold_uncertainty_score":0.9998907,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02201006462590525,"score_gpt":0.2129317058953956,"score_spread":0.1909216412694904,"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."}}