{"id":"W2922423793","doi":"10.1080/00207721.2019.1586005","title":"Stochastic stability analysis for neutral-type Markov jump neural networks with additive time-varying delays via a new reciprocally convex combination inequality","year":2019,"lang":"en","type":"article","venue":"International Journal of Systems Science","topic":"Neural Networks Stability and Synchronization","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"China Scholarship Council; Government of Jiangsu Province; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Stability (learning theory); Type (biology); Convex combination; Mathematics; Artificial neural network; Regular polygon; Markov chain; Linear matrix inequality; Control theory (sociology); Markov process; Jump; Applied mathematics; Computer science; Mathematical optimization; Convex optimization; Control (management); Artificial intelligence; Statistics; Machine learning; Geology","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001614117,0.001479305,0.0007761543,0.0005923954,0.0003937467,0.001286342,0.00109561,0.0007980978,0.002360514],"category_scores_gemma":[0.002440611,0.0003408614,0.001022909,0.0004999528,0.0009799999,0.001678757,0.001227682,0.001692063,0.0002797385],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001211244,"about_ca_system_score_gemma":0.0009932735,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002134494,"about_ca_topic_score_gemma":0.001467243,"domain_scores_codex":[0.9991686,0.0002300858,0.00005271805,0.0001802528,0.0002795713,0.0000887466],"domain_scores_gemma":[0.9992601,0.000357236,0.0001162481,0.000030881,0.000200264,0.00003518588],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00008337105,0.0000324204,0.0004434643,0.0001815889,0.0000846821,0.0001996263,0.0001252207,0.7976077,0.0108271,0.1682146,0.00108949,0.02111079],"study_design_scores_gemma":[0.000002605658,0.00001927348,0.00005055534,0.000004142504,0.000007782493,0.00001787768,0.000006485584,0.9905501,0.000566734,0.008468818,0.0003002605,0.000005420573],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007074013,0.000209988,0.9880868,0.0001508726,0.00003878676,0.00002165836,0.00003801331,0.00003398226,0.004345803],"genre_scores_gemma":[0.8949174,0.001463531,0.0942867,0.00019304,0.0001644395,0.0002358049,0.0002156089,0.00008235122,0.008441125],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002360514,"threshold_uncertainty_score":0.008788228,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01710617687085435,"score_gpt":0.2565000491806516,"score_spread":0.2393938723097973,"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."}}