Sufficient Conditions for Persistency of Excitation with Step and ReLU Activation Functions
Optimization and Control
2022-09-16 v2
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.
Keywords
Cite
@article{arxiv.2209.06286,
title = {Sufficient Conditions for Persistency of Excitation with Step and ReLU Activation Functions},
author = {Tyler Lekang and Andrew Lamperski},
journal= {arXiv preprint arXiv:2209.06286},
year = {2022}
}