Litcius/Paper detail

Sliding Mode Control-Based Synchronization of Complex-Valued Neural Networks

Eugenia Di Palo, Josep M. Olm, Arnau Dòria‐Cerezo, Mario di Bernardo

2023IEEE Transactions on Control of Network Systems10 citationsDOIOpen Access PDF

Abstract

Synchronization is a typical dynamical behaviour of interconnected systems that is being extensively studied in neural networks. However, most of the research considers real-valued neural networks, and less results have been obtained on their complex-valued counterparts. This work presents two sliding mode control strategies to achieve synchronization in a complex-valued neural network. The former simplifies an already existing technique that splits the control into real and imaginary parts. The latter extends a fully complex-valued sliding approach for generic complex-valued dynamical systems to the multi-input multi-output case, and shows its efficiency and higher performance in terms of finite reaching time in the synchronization of complex-valued neural networks. The approach is validated via numerical simulations.

Topics & Concepts

Synchronization (alternating current)Artificial neural networkSliding mode controlComputer scienceComplex networkControl theory (sociology)Complex systemDynamical systems theoryMode (computer interface)Control (management)Artificial intelligenceNonlinear systemTelecommunicationsPhysicsWorld Wide WebQuantum mechanicsChannel (broadcasting)Operating systemNeural Networks Stability and SynchronizationNeural Networks and ApplicationsNeural dynamics and brain function
Sliding Mode Control-Based Synchronization of Complex-Valued Neural Networks | Litcius