Dec 15, 2023 · Zhang, "Towards robust neural networks via close-loop control," International Conference on Learning Representation (ICLR), May 2021, 22 pages. (*Equal ...

Jun 13, 2024 · Towards robust neural networks via close-loop control. arXiv preprint arXiv ... Adv-bnn: Improved adversarial defense through robust bayesian neural network.

Jan 15, 2024 · In this paper we propose a method to train a neural network in closed loop for control systems, in continuous or discrete time, while allowing for flexible ...

Oct 5, 2023 · The proposed low-rank, sparse connectivity induces an interpretable prior on the network that proves to be most amenable for a class of models known as closed- ...

Aug 15, 2023 · Towards Robust Neural Networks via Close-Loop Control. In International Conference on Learning Representations; 2020. (34) Ren, Z.; Oviedo, F.; Thway, M.; Tian, ...

Apr 2, 2024 · The method assumes perturbations and threats exist directly in the continuous embedding space of neural networks. However, most real-world adversarial attacks ...

May 14, 2024 · Towards robust neural networks via close-loop control. arXiv preprint arXiv ... Towards robust neural networks via random self-ensemble. In Proceedings ...

Jul 14, 2023 · Other rigorous approaches for verification of closed-loop neural network controllers include using finite-state abstractions (Sun et al., 2019) and structured.

Dec 6, 2023 · The pruning objective has recently extended be- yond accuracy and sparsity to robustness in lan- guage models. Despite this, existing methods.

Nov 22, 2023 · Abstract. This paper addresses the design of controllers for systems modelled as recurrent neural networks (RNNs). A novel data-based procedure for the design ...