{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002462316,0.0001944433,0.0004391941,0.0004284607,0.0001686901,0.0005613134,0.001708192,0.00007056069,0.00002505004],"category_scores_gemma":[0.0002827261,0.0001560021,0.0001554218,0.001949627,0.0001862215,0.002485394,0.0001663123,0.0002528719,0.000005417774],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004435147,"about_ca_system_score_gemma":0.0005305654,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009278919,"about_ca_topic_score_gemma":0.00002315225,"domain_scores_codex":[0.9968649,0.0001986093,0.0008615982,0.000511695,0.001216013,0.0003472114],"domain_scores_gemma":[0.9940404,0.0006650767,0.001010544,0.0003664487,0.003695573,0.0002219955],"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":[0.0004362728,0.0001402352,0.01070967,0.00002058797,0.0002390636,0.000009514487,0.0005509947,0.9804703,0.001387276,0.001791841,0.00007468644,0.004169581],"study_design_scores_gemma":[0.0008101427,0.0005905385,0.006828944,0.00008078266,0.00005492431,0.00009179861,0.00003952165,0.9907383,0.0001733845,0.0003965648,0.00001498807,0.000180115],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2627164,0.00004992197,0.7343593,0.0003886687,0.002015031,0.0004000618,0.000006229616,0.00002454208,0.00003987979],"genre_scores_gemma":[0.9957502,0.000003387362,0.0037509,0.0001184007,0.0003035257,0.000006327224,0.00001350329,0.000008308574,0.00004545092],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7330338,"threshold_uncertainty_score":0.6361582,"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."}}