Efficient Reachability Analysis for Convolutional Neural Networks Using Hybrid Zonotopes
This work introduces an efficient approach to compute the reachable sets for convolutional neural networks.
Mar 13, 2025
Hybrid Zonotope-Based Backward Reachability Analysis for Neural Feedback Systems With Nonlinear Plant Models
This work introduces a novel approach to compute the over-approximation of backward reachable sets for neural feedback systems with non-linear plant models and general activation functions.
Sep 5, 2024
Reachability Analysis of Neural Network Control Systems With Tunable Accuracy and Efficiency
This paper introduces a novel tunable hybrid zonotope-based method for computing both forward and backward reachable sets of neural network control systems.
Jun 17, 2024
Presentation at 2023 IEEE CDC
A novel approach for computing the exact backward reachable sets of neural feedback systems.
Dec 15, 2023
Reachability Analysis and Safety Verification of Neural Feedback Systems via Hybrid Zonotopes
This paper presents novel hybrid zonotope-based methods for the reachability analysis and safety verification of neural feedback systems. Algorithms are proposed to compute the input-output relationship of each layer of a feed-forward neural network, as well as the exact reachable sets of neural feedback systems.
Jul 3, 2023
Backward Reachability Analysis of Neural Feedback Systems Using Hybrid Zonotopes
A novel approach for computing the exact backward reachable sets of neural feedback systems.
Jun 26, 2023
Safety Verification of Neural Feedback Systems Based on Constrained Zonotopes
A novel set-based method is proposed to compute both exact and over-approximated reachable sets for neural feedback systems.
Jan 10, 2023
Presentation at 2022 IEEE CDC
A novel set-based method is proposed to compute both exact and over-approximated reachable sets for neural feedback systems.
Dec 7, 2022