3 papers
math.OC2026
Forward and Backward Reachability Analysis of Closed-loop Recurrent Neural Networks via Hybrid Zonotopes
Yuhao Zhang, Xiangru Xu
Recurrent neural networks (RNNs) are widely employed to model complex dynamical systems due to their hidden-state structure, which inherently captures temporal dependencies. This w…
math.OC2025
Efficient Reachability Analysis for Convolutional Neural Networks Using Hybrid Zonotopes
Yuhao Zhang, Xiangru Xu
Feedforward neural networks are widely used in autonomous systems, particularly for control and perception tasks within the system loop. However, their vulnerability to adversarial…
math.OC2025
Robust Stability of Neural Network Control Systems with Interval Matrix Uncertainties
Yuhao Zhang, Xiangru Xu
Neural networks have become increasingly popular in controller design due to their versatility and efficiency. However, their integration into feedback systems can pose stability c…