Showing math.OCShow all
3 papers · 1 filter
math.OC2026
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…
math.OC2026
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…
math.OC2025
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…