Relaxed Stability Criteria for Delayed Generalized Neural Networks via a Novel Reciprocally Convex Combination
Yibo Wang, Changchun Hua, PooGyeon Park
Abstract
Dear Editor, This letter examines the stability issue of generalized neural networks (GNNs) with time-varying delay based on a novel reciprocally convex combination (RCC). By considering a new matrix polynomial, the proposed novel reciprocally convex method leads to a tight bound for integral inequality combination and encompasses several existing approaches as special cases. The relaxed stability conditions with less conservatism are developed by employing the proposed reciprocally convex combination and the Lyapunov-Krasovskii (L-K) functional. Finally, several numerical examples are conducted to show the superiorities of the stability conditions.
Topics & Concepts
Convex combinationStability (learning theory)Linear matrix inequalityRegular polygonMathematicsArtificial neural networkConvex optimizationConservatismPolynomialMatrix (chemical analysis)Stability conditionsUpper and lower boundsComputer scienceApplied mathematicsMathematical optimizationMathematical analysisArtificial intelligenceMachine learningPolitical scienceLawGeometryDiscrete time and continuous timeComposite materialMaterials scienceStatisticsPoliticsNeural Networks Stability and SynchronizationNeural Networks and ApplicationsAdvanced Memory and Neural Computing