{"id":"W2907997710","doi":"10.1016/j.neucom.2018.12.028","title":"Stochastic stability criterion of neutral-type neural networks with additive time-varying delay and uncertain semi-Markov jump","year":2018,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Neural Networks Stability and Synchronization","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"National Natural Science Foundation of China","keywords":"Mathematics; Stability (learning theory); Convex combination; Markov chain; Artificial neural network; Markov process; Applied mathematics; Type (biology); Regular polygon; Control theory (sociology); Mathematical optimization; Computer science; Convex optimization; Statistics; Control (management); Machine learning; 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":[0.0003760036,0.0002589559,0.0003206286,0.00007863637,0.0003564479,0.0001393516,0.0004082141,0.00008447155,0.00002078355],"category_scores_gemma":[0.00009506432,0.0002306052,0.00004518463,0.0007995203,0.0002935127,0.0004826749,0.0003780194,0.000300335,0.000003535078],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004036001,"about_ca_system_score_gemma":0.00005294906,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000311994,"about_ca_topic_score_gemma":0.00001925504,"domain_scores_codex":[0.9978234,0.0003139655,0.000418826,0.0007324268,0.0002357464,0.0004756001],"domain_scores_gemma":[0.9981657,0.0006439292,0.0002370286,0.0004527823,0.0003693664,0.0001311426],"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":[0.0004623953,0.0002314374,0.006357778,0.0001726474,0.00005352278,0.00005696715,0.003466154,0.8608001,0.005032536,0.000580824,0.0002280799,0.1225576],"study_design_scores_gemma":[0.0003295179,0.0007243092,0.0025483,0.00008317701,0.00001302854,0.00006724977,0.0000142763,0.995275,0.0006120014,0.00009807121,0.00001615514,0.0002189179],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5924847,0.00004495582,0.406668,0.0001137986,0.000220831,0.0002712234,0.000001984418,0.0001227686,0.0000717758],"genre_scores_gemma":[0.9938877,0.000003232548,0.005526885,0.0002717727,0.0002700305,0.000003736233,0.00001076266,0.0000205388,0.00000529175],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4014031,"threshold_uncertainty_score":0.9403805,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01399682079563648,"score_gpt":0.2346035015686778,"score_spread":0.2206066807730413,"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."}}