{"id":"W3130804812","doi":"10.1109/tnnls.2021.3059389","title":"Input-to-State Representation in Linear Reservoirs Dynamics","year":2021,"lang":"en","type":"preprint","venue":"IEEE Transactions on Neural Networks and Learning Systems","topic":"Neural Networks and Reservoir Computing","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"Canada Research Chairs; European Commission","keywords":"Computer science; Controllability; Simplicity; Salient; Simple (philosophy); Representation (politics); Gradient descent; Heuristics; Reservoir computing; Recurrent neural network; Rank (graph theory); Measure (data warehouse); State (computer science); Theoretical computer science; Network dynamics; Matrix (chemical analysis); Topology (electrical circuits); Artificial neural network; Artificial intelligence; Algorithm; Mathematics; Data mining; Applied mathematics","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0007667373,0.000521683,0.0007462095,0.0004476693,0.0005158566,0.001125455,0.0008250909,0.000391972,0.000002517008],"category_scores_gemma":[0.00002225576,0.0005091859,0.0002206415,0.001157988,0.00004785898,0.0003132347,0.0001174519,0.003879643,0.000003428826],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001674889,"about_ca_system_score_gemma":0.00006075266,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001227961,"about_ca_topic_score_gemma":0.0006154464,"domain_scores_codex":[0.9952784,0.001202267,0.0008771481,0.001425573,0.0004964323,0.0007202492],"domain_scores_gemma":[0.9977888,0.0005398266,0.0003347555,0.0008765998,0.0001690639,0.0002909235],"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":[0.0000309894,0.0000516582,0.0003457526,0.0001124977,0.000038511,0.0001608456,0.0005340338,0.9727543,0.000009905688,0.00001619259,0.00004417332,0.02590117],"study_design_scores_gemma":[0.000305962,0.0001586992,0.0004221342,0.0009140045,0.00001354522,0.00006027479,0.0002024007,0.9972991,0.00001335462,0.00001460006,0.00010123,0.0004946581],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2485273,0.0005366735,0.7440516,0.0007151429,0.005282044,0.0005997401,0.000003058901,0.0002470122,0.00003751238],"genre_scores_gemma":[0.9964691,0.0004185381,0.001492198,0.0001672651,0.0003384165,0.00009927674,0.00001929757,0.00006009145,0.0009357579],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7479419,"threshold_uncertainty_score":0.9999115,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01981652622111789,"score_gpt":0.2620013356307601,"score_spread":0.2421848094096422,"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."}}