{"id":"W4389952311","doi":"10.1140/epjp/s13360-023-04772-x","title":"A memristor-coupled heterogeneous discrete neural networks with infinite multi-structure hyperchaotic attractors","year":2023,"lang":"en","type":"article","venue":"The European Physical Journal Plus","topic":"Neural Networks Stability and Synchronization","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":false,"ca_institutions":"Professional Engineers Ontario","funders":"National Natural Science Foundation of China","keywords":"Memristor; Attractor; Computer science; Correctness; Artificial neural network; Stability (learning theory); Coupling (piping); Topology (electrical circuits); Property (philosophy); Control theory (sociology); Basis (linear algebra); Algorithm; Artificial intelligence; Mathematics; Electronic engineering; Machine learning; Engineering; Mathematical analysis","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":[],"consensus_categories":[],"category_scores_codex":[0.0004530054,0.0002800453,0.0002720168,0.00006432874,0.0006222742,0.0004456974,0.00125896,0.00003159964,0.000003935135],"category_scores_gemma":[0.00004252257,0.0001582037,0.0001576318,0.0008314801,0.0001776766,0.000455306,0.0003632013,0.0009193026,0.00004887172],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008130888,"about_ca_system_score_gemma":0.00003391136,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000645587,"about_ca_topic_score_gemma":0.0000150931,"domain_scores_codex":[0.9974694,0.0008759147,0.0002992221,0.000364762,0.000451229,0.0005394893],"domain_scores_gemma":[0.998619,0.000278609,0.0002009905,0.0005814246,0.00009778475,0.0002222383],"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":[0.00004950532,0.00003386358,0.0001193894,0.000007605848,0.00004708132,0.0004739963,0.001347733,0.9811063,0.0008042569,0.0001392647,0.0001721932,0.01569876],"study_design_scores_gemma":[0.0005714747,0.0001955273,0.004126848,0.00002603419,0.0000258702,0.0005222279,0.00002169353,0.9936197,0.0000314824,0.0005388933,0.00008183916,0.0002384343],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7713746,0.0000654869,0.2260493,0.0010113,0.000695848,0.0002408999,0.000003742776,0.0003502926,0.0002084702],"genre_scores_gemma":[0.9975631,0.00002027667,0.0003702985,0.0002572555,0.00166578,0.000001416243,0.000007939712,0.00004694342,0.00006700706],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2261884,"threshold_uncertainty_score":0.6451361,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02247358427247578,"score_gpt":0.2412926899503329,"score_spread":0.2188191056778571,"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."}}