5 papers
Chaos-Free Networks are Stable Recurrent Neural Networks
Stefano De Carli, Davide Previtali, Mirko Mazzoleni +1
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 ar…
Stability properties of Minimal Gated Unit neural networks
Stefano De Carli, Davide Previtali, Mirko Mazzoleni +1
In this work, we address the need for efficient and formally stable Recurrent Neural Networks (RNNs) in environments with limited computational resources by analyzing the stability…
A virtual sensor fusion approach for state of charge estimation of lithium-ion cells
Davide Previtali, Daniele Masti, Mirko Mazzoleni +1
This paper addresses the estimation of the State Of Charge (SOC) of lithium-ion cells via the combination of two widely used paradigms: Kalman Filters (KFs) equipped with Equivalen…
Integrating Biological-Informed Recurrent Neural Networks for Glucose-Insulin Dynamics Modeling
Stefano De Carli, Nicola Licini, Davide Previtali +2
Type 1 Diabetes (T1D) management is a complex task due to many variability factors. Artificial Pancreas (AP) systems have alleviated patient burden by automating insulin delivery t…
Infinity-norm-based Input-to-State-Stable Long Short-Term Memory networks: a thermal systems perspective
Stefano De Carli, Davide Previtali, Leandro Pitturelli +3
Recurrent Neural Networks (RNNs) have shown remarkable performances in system identification, particularly in nonlinear dynamical systems such as thermal processes. However, stabil…