{"id":"W2554286264","doi":"10.1007/s11063-016-9563-5","title":"Dynamical Behavior of Complex-Valued Hopfield Neural Networks with Discontinuous Activation Functions","year":2016,"lang":"en","type":"article","venue":"Neural Processing Letters","topic":"Neural Networks Stability and Synchronization","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"Natural Science Foundation of Hainan Province; National Natural Science Foundation of China","keywords":"Artificial neural network; Differential inclusion; Mathematics; Complex system; Hopfield network; Convergence (economics); Lyapunov function; Set (abstract data type); Dynamical systems theory; Stability (learning theory); Applied mathematics; Function (biology); Computational intelligence; Computer science; Nonlinear system; Mathematical optimization; Artificial intelligence","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":[0.00009637744,0.0001943721,0.0002233797,0.00007550205,0.0002220373,0.0001333568,0.0004119113,0.00006846914,0.00001330408],"category_scores_gemma":[0.00002623307,0.0001246403,0.00006380465,0.0004492964,0.0002086432,0.001197997,0.0000928697,0.0001842868,0.000001346784],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005435559,"about_ca_system_score_gemma":0.00002763762,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001704488,"about_ca_topic_score_gemma":0.00002024776,"domain_scores_codex":[0.9984691,0.00009975558,0.000317396,0.0004489915,0.0003101767,0.0003546332],"domain_scores_gemma":[0.9991342,0.0001087193,0.0002211273,0.0003513924,0.0001055245,0.00007899984],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001876691,0.0002409035,0.02171596,0.00007523689,0.00002419602,0.0000254678,0.0004024816,0.04092947,0.1511725,0.0004268519,0.0008210305,0.7839782],"study_design_scores_gemma":[0.0007257044,0.0002256562,0.03663462,0.00010189,0.00002910398,0.00004444574,0.0000238512,0.9607522,0.001068968,0.00004109686,0.00003995611,0.0003124439],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4495019,0.000007082832,0.5443957,0.005687817,0.0001313642,0.000146507,0.000001377304,0.0001116378,0.00001665769],"genre_scores_gemma":[0.9956738,6.978802e-7,0.003003638,0.001100038,0.000127925,0.00002748651,0.00001018944,0.00001653346,0.0000396859],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9198228,"threshold_uncertainty_score":0.5082683,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01765384205709101,"score_gpt":0.2322988420225103,"score_spread":0.2146449999654193,"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."}}