Litcius/Paper detail

An adaptive gradient-descent-based neural networks for the on-line solution of linear time variant equations and its applications

Jun Cai, Chenfu Yi

2022Information Sciences21 citationsDOIOpen Access PDF

Abstract

It is well-known that, the classical gradient-descent-based neural network (CGNN) model is used widely for the time-invariant problem solving. However, it is an extremely common problem for the time varying cases in the practical engineering applications, while the CGNN effective neural solver for the time-variant problems. For this reason, in this article, an adaptive GNN (AGNN) is presented for the linear time variant matrix equation (LTVME) on-line solving based on Lyapunov theory. Theoretical analysis already verified that the presented AGNN model could achieve the correct state solution effectively. The simulated experiment results further validate that the state solution of the AGNN model could be convergent to the correct solution of the solved time variant problems in theory.

Topics & Concepts

Gradient descentArtificial neural networkComputer scienceDescent (aeronautics)SolverMathematical optimizationApplied mathematicsLyapunov functionMatrix (chemical analysis)MathematicsNonlinear systemArtificial intelligenceAerospace engineeringPhysicsQuantum mechanicsComposite materialMaterials scienceEngineeringNeural Networks and ApplicationsAdvanced Numerical Analysis TechniquesModel Reduction and Neural Networks
An adaptive gradient-descent-based neural networks for the on-line solution of linear time variant equations and its applications | Litcius