Sufficient Conditions for Persistency of Excitation with Step and ReLU Activation Functions

arXiv2209.06286MaRDI QIDQ6410657FDOQ6410657

Publication date: 13 September 2022

Abstract: This paper defines geometric criteria which are then used to establish sufficient conditions for persistency of excitation with vector functions constructed from single hidden-layer neural networks with step or ReLU activation functions. We show that these conditions hold when employing reference system tracking, as is commonly done in adaptive control. We demonstrate the results numerically on a system with linearly parameterized activations of this type and show that the parameter estimates converge to the true values with the sufficient conditions met.

Has companion code repository: https://github.com/tylerlekang/cdc2022

This page was built for publication: Sufficient Conditions for Persistency of Excitation with Step and ReLU Activation Functions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6410657)