{"id":"W2742381771","doi":"10.1007/s00521-017-3166-6","title":"Exponential stability analysis for delayed complex-valued memristor-based recurrent neural networks","year":2017,"lang":"en","type":"article","venue":"Neural Computing and Applications","topic":"Neural Networks Stability and Synchronization","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"Lakehead University","funders":"National Natural Science Foundation of China","keywords":"Memristor; Uniqueness; Exponential stability; Lyapunov function; Equilibrium point; Mathematics; Artificial neural network; Stability (learning theory); Applied mathematics; Extension (predicate logic); Computational Science and Engineering; Exponential function; Matrix (chemical analysis); Function (biology); Computer science; Control theory (sociology); Differential equation; Artificial intelligence; Mathematical analysis; Nonlinear system","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":[0.0004452295,0.0002203516,0.0003350592,0.0000793385,0.002353895,0.0006243006,0.0009492298,0.00008187427,0.000006369019],"category_scores_gemma":[0.00005384859,0.0002165807,0.000217203,0.0003704748,0.0001958165,0.0002685356,0.0002945426,0.0001999598,8.830884e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005217836,"about_ca_system_score_gemma":0.0000261926,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006079461,"about_ca_topic_score_gemma":0.0001025597,"domain_scores_codex":[0.9980481,0.0001422584,0.0004375339,0.0007795951,0.0002042655,0.0003882718],"domain_scores_gemma":[0.9977008,0.0003215092,0.0003744049,0.001232751,0.0002079668,0.0001625304],"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":[0.0001313523,0.0005506369,0.03419271,0.0001201785,0.0002676825,0.00000207843,0.0003316311,0.5924683,0.0005990598,0.0265654,0.000555239,0.3442158],"study_design_scores_gemma":[0.0004288357,0.00008364261,0.02555251,0.000003677354,0.00009930928,0.000001550981,0.000007112856,0.9727177,0.00005355394,0.00038853,0.0004473405,0.0002162482],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1193536,0.00007461233,0.8782223,0.001164588,0.0002078874,0.0007271814,0.00002007597,0.0001929493,0.00003682564],"genre_scores_gemma":[0.9844774,0.000003182085,0.01480408,0.0001935268,0.0002886927,0.0001008804,0.0001164851,0.00001095099,0.00000477539],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8651239,"threshold_uncertainty_score":0.9989449,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05326504425275801,"score_gpt":0.308943583025835,"score_spread":0.2556785387730769,"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."}}