{"id":"W2758428971","doi":"10.1109/tcyb.2017.2751005","title":"Marginally Stable Triangular Recurrent Neural Network Architecture for Time Series Prediction","year":2017,"lang":"en","type":"article","venue":"IEEE Transactions on Cybernetics","topic":"Neural Networks and Reservoir Computing","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"Saint Mary's University","funders":"","keywords":"Triangular matrix; Artificial neural network; Computer science; Eigenvalues and eigenvectors; Control theory (sociology); Block (permutation group theory); Discrete time and continuous time; Diagonal; Network architecture; Algorithm; Mathematics; Artificial intelligence; Geometry; Pure 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":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0002494503,0.0002366015,0.0002471341,0.00006253824,0.001310061,0.0005659647,0.001006502,0.0001162287,0.00001547127],"category_scores_gemma":[0.000009398721,0.0002097657,0.0001948689,0.0001308893,0.00008335913,0.0003600456,0.00001508423,0.0003670169,0.0000155529],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003972585,"about_ca_system_score_gemma":0.00004424883,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000133028,"about_ca_topic_score_gemma":0.00003845372,"domain_scores_codex":[0.9983785,0.00007180632,0.0002903706,0.0004628038,0.0002789058,0.000517608],"domain_scores_gemma":[0.99858,0.0001313459,0.0001839742,0.0008621701,0.0001018907,0.0001405883],"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":[0.0001188362,0.00009328149,0.00001601567,0.00002662244,0.00005085048,0.0000102424,0.0001155908,0.8167777,0.0002153538,0.0004853803,0.003471064,0.1786191],"study_design_scores_gemma":[0.0009139344,0.0007201213,0.0005737181,0.0001142417,0.00004727162,0.00004490538,0.000004017847,0.9691592,0.00203268,0.00270814,0.02334135,0.0003403928],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007054348,0.0001127754,0.9860796,0.002377731,0.003227889,0.0005421072,0.0000354342,0.0002189894,0.0003511494],"genre_scores_gemma":[0.8755671,0.000166685,0.1143039,0.0003200616,0.001656373,0.0001288639,0.00001161907,0.00007391898,0.007771444],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8717757,"threshold_uncertainty_score":0.9999901,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01591524904987858,"score_gpt":0.2395324549458908,"score_spread":0.2236172058960122,"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."}}