Litcius/Paper detail

Delay dependent complex-valued bidirectional associative memory neural networks with stochastic and impulsive effects: an exponential stability approach

C. Maharajan, C. Sowmiya, Changjin Xu

2024Kybernetika21 citationsDOIOpen Access PDF

Abstract

summary:This paper investigates the stability in an exponential sense of complex-valued Bidirectional Associative Memory (BAM) neural networks with time delays under the stochastic and impulsive effects. By utilizing the contracting mapping theorem, the existence and uniqueness of the equilibrium point for the proposed complex-valued neural networks are verified. Moreover, based on the Lyapunov - Krasovskii functional construction, matrix inequality techniques and stability theory, some novel time-delayed sufficient conditions are attained in linear matrix inequalities (LMIs) form, which ensure the exponential stability of the trivial solution for the addressed neural networks. Finally, to illustrate the superiority and effects of our theoretical results, two numerical examples with their simulations are provided via MATLAB LMI control toolbox.

Topics & Concepts

Bidirectional associative memoryContent-addressable memoryArtificial neural networkExponential stabilityStability (learning theory)Computer scienceAssociative propertyMathematicsApplied mathematicsArtificial intelligencePure mathematicsNonlinear systemMachine learningPhysicsQuantum mechanicsNeural Networks and ApplicationsNeural Networks Stability and SynchronizationMachine Learning and ELM