Data-driven stability assessment of multilayer long short-term memory networks

Grande, Davide; Harris, Catherine A.; Thomas, Giles; Anderlini, Enrico. 2021 Data-driven stability assessment of multilayer long short-term memory networks. Applied Sciences, 11 (4), 1829.

Before downloading, please read NORA policies.
applsci-11-01829.pdf - Published Version
Available under License Creative Commons Attribution 4.0.

Download (1MB) | Preview


Recurrent Neural Networks (RNNs) are increasingly being used for model identification, forecasting and control. When identifying physical models with unknown mathematical knowledge of the system, Nonlinear AutoRegressive models with eXogenous inputs (NARX) or Nonlinear AutoRegressive Moving-Average models with eXogenous inputs (NARMAX) methods are typically used. In the context of data-driven control, machine learning algorithms are proven to have comparable performances to advanced control techniques, but lack the properties of the traditional stability theory. This paper illustrates a method to prove a posteriori the stability of a generic neural network, showing its application to the state-of-the-art RNN architecture. The presented method relies on identifying the poles associated with the network designed starting from the input/output data. Providing a framework to guarantee the stability of any neural network architecture combined with the generalisability properties and applicability to different fields can significantly broaden their use in dynamic systems modelling and control.

Item Type: Publication - Article
Digital Object Identifier (DOI):
ISSN: 2076-3417
Date made live: 22 Mar 2021 11:32 +0 (UTC)

Actions (login required)

View Item View Item

Document Downloads

Downloads for past 30 days

Downloads per month over past year

More statistics for this item...