Chaos-Free Networks are Stable Recurrent Neural Networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: De Carli, Stefano, Previtali, Davide, Mazzoleni, Mirko, Previdi, Fabio
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911515916894208
author De Carli, Stefano
Previtali, Davide
Mazzoleni, Mirko
Previdi, Fabio
author_facet De Carli, Stefano
Previtali, Davide
Mazzoleni, Mirko
Previdi, Fabio
contents Gated Recurrent Neural Networks (RNNs) are widely used for nonlinear system identification due to their high accuracy, although they often exhibit complex, chaotic dynamics that are difficult to analyze. This paper investigates the system-theoretic properties of the Chaos-Free Network (CFN), an architecture originally proposed to eliminate the chaotic behavior found in standard gated RNNs. First, we formally prove that the CFN satisfies Input-to-State Stability (ISS) by design. However, we demonstrate that ensuring Incremental ISS (delta-ISS) still requires specific parametric constraints on the CFN architecture. Then, to address this, we introduce the Decoupled-Gate Network (DGN), a novel structural variant of the CFN that removes internal state connections in the gating mechanisms. Finally, we prove that the DGN unconditionally satisfies the delta-ISS property, providing an incrementally stable architecture for identifying nonlinear dynamical systems without requiring complex network training modifications. Numerical results confirm that the DGN maintains the modeling capabilities of standard architectures while adhering to these rigorous stability guarantees.
format Preprint
id arxiv_https___arxiv_org_abs_2603_14106
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Chaos-Free Networks are Stable Recurrent Neural Networks
De Carli, Stefano
Previtali, Davide
Mazzoleni, Mirko
Previdi, Fabio
Optimization and Control
Systems and Control
93D05, 37N35, 68T07
I.2.6
Gated Recurrent Neural Networks (RNNs) are widely used for nonlinear system identification due to their high accuracy, although they often exhibit complex, chaotic dynamics that are difficult to analyze. This paper investigates the system-theoretic properties of the Chaos-Free Network (CFN), an architecture originally proposed to eliminate the chaotic behavior found in standard gated RNNs. First, we formally prove that the CFN satisfies Input-to-State Stability (ISS) by design. However, we demonstrate that ensuring Incremental ISS (delta-ISS) still requires specific parametric constraints on the CFN architecture. Then, to address this, we introduce the Decoupled-Gate Network (DGN), a novel structural variant of the CFN that removes internal state connections in the gating mechanisms. Finally, we prove that the DGN unconditionally satisfies the delta-ISS property, providing an incrementally stable architecture for identifying nonlinear dynamical systems without requiring complex network training modifications. Numerical results confirm that the DGN maintains the modeling capabilities of standard architectures while adhering to these rigorous stability guarantees.
title Chaos-Free Networks are Stable Recurrent Neural Networks
topic Optimization and Control
Systems and Control
93D05, 37N35, 68T07
I.2.6
url https://arxiv.org/abs/2603.14106