$l_2$ Induced Norm Analysis of Discrete-Time LTI Systems for Nonnegative Input Signals and Its Application to Stability Analysis of Recurrent Neural Networks - Équipe Méthodes et Algorithmes en Commande
Journal Articles European Journal of Control Year : 2021

$l_2$ Induced Norm Analysis of Discrete-Time LTI Systems for Nonnegative Input Signals and Its Application to Stability Analysis of Recurrent Neural Networks

Abstract

In this paper, we focus on the "positive" $l_2$ induced norm of discrete-time linear time-invariant systems where the input signals are restricted to be nonnegative. To cope with the nonnegativity of the input signals, we employ copositive programming as the mathematical tool for the analysis. Then, by applying an inner approximation to the copositive cone, we derive numerically tractable semidefinite programming problems for the upper and lower bound computation of the "positive" $l_2$ induced norm. This norm is typically useful for the stability analysis of feedback systems constructed from an LTI system and nonlinearities where the nonlinear elements provide only nonnegative signals. As a concrete example, we illustrate the usefulness of the "positive" $l_2$ induced norm for the stability analysis of recurrent neural networks with activation functions being rectified linear units.

Dates and versions

hal-03026445 , version 1 (26-11-2020)

Identifiers

Cite

Yoshio Ebihara, Hayato Waki, Victor Magron, Ngoc Hoang Anh Mai, Dimitri Peaucelle, et al.. $l_2$ Induced Norm Analysis of Discrete-Time LTI Systems for Nonnegative Input Signals and Its Application to Stability Analysis of Recurrent Neural Networks. European Journal of Control, 2021, 62, pp.99-104. ⟨10.1016/j.ejcon.2021.06.022⟩. ⟨hal-03026445⟩
64 View
0 Download

Altmetric

Share

More