On the stability properties of Gated Recurrent Units neural networks

Abstract

The goal of this paper is to provide sufficient conditions for guaranteeing the Input-to-State Stability (ISS) and the Incremental Input-to-State Stability (δISS) of Gated Recurrent Units (GRUs) neural networks. These conditions, devised for both single-layer and multi-layer architectures, consist of nonlinear inequalities on network's weights. They can be employed to check the stability of trained networks, or can be enforced as constraints during the training procedure of a GRU. The resulting training procedure is tested on a Quadruple Tank nonlinear benchmark system, showing satisfactory modeling performances.

arXiv commentCopyright 2021. This manuscript version is made available under the CC-BY-NC-ND 4.0

References in corpus (5)

• Nonlinear Systems Identification Using Deep Dynamic Neural Networks
• Stable Recurrent Models
• On the stability properties of Gated Recurrent Units neural networks
• LSTM Neural Networks: Input to State Stability and Probabilistic Safety Verification
• Model predictive control design for dynamical systems learned by Long Short-Term Memory Networks

Cited by in corpus (13)

• On Recurrent Neural Networks for learning-based control: recent results and ideas for future developments
• On the stability properties of Gated Recurrent Units neural networks
• Nonlinear MPC for Offset-Free Tracking of systems learned by GRU Neural Networks
• Stability of discrete-time feed-forward neural networks in NARX configuration
• Recurrent Neural Network-based Internal Model Control design for stable nonlinear systems
• Nonlinear MPC design for incrementally ISS systems with application to GRU networks
• Robust constrained nonlinear Model Predictive Control with Gated Recurrent Unit model -- Extended version
• Robust offset-free constrained Model Predictive Control with Long Short-Term Memory Networks -- Extended version
• An Offset-Free Nonlinear MPC scheme for systems learned by Neural NARX models
• Towards lifelong learning of Recurrent Neural Networks for control design
• Robust offset-free nonlinear model predictive control for systems learned by neural nonlinear autoregressive exogenous models
• Input State Stability of Gated Graph Neural Networks
• Latent-Lagrangian Neural Networks for Reduced Order Modeling of Non-autonomous Nonlinear Dynamical Systems