A new approach for combined model class selection and parameters learning for auto-regressive neural models

TL;DR

This paper presents a novel set-membership based method for joint model class selection and parameter learning in nonlinear auto-regressive neural models, improving robustness and accuracy for control applications.

Contribution

It introduces a new approach that simultaneously selects model structure and learns parameters for NARXESNs using set-membership techniques, enhancing robustness and efficiency.

Findings

Effective identification of parsimonious models

Robust training accounting for measurement noise

Improved model accuracy for control applications

Abstract

This work introduces a novel approach for the joint selection of model structure and parameter learning for nonlinear dynamical systems identification. Focusing on a specific Recurrent Neural Networks (RNNs) family, i.e., Nonlinear Auto-Regressive with eXogenous inputs Echo State Networks (NARXESNs), the method allows to simultaneously select the optimal model class and learn model parameters from data through a new set-membership (SM) based procedure. The results show the effectiveness of the approach in identifying parsimonious yet accurate models suitable for control applications. Moreover, the proposed framework enables a robust training strategy that explicitly accounts for bounded measurement noise and enhances model robustness by allowing data-consistent evaluation of simulation performance during parameter learning, a process generally NP-hard for models with autoregressive components.