no code implementations • 6 Apr 2024 • Chuqin Geng, Zhaoyue Wang, Haolin Ye, Saifei Liao, Xujie Si
In this paper, we study the following problem: Given a neural network, find a minimal (coarsest) NAP that is sufficient for formal verification of the network's robustness.
no code implementations • 23 Jan 2024 • Zhaoyue Wang
When we design and deploy an Reinforcement Learning (RL) agent, reward functions motivates agents to achieve an objective.
no code implementations • 9 Nov 2023 • Sihan Gao, Jing Zhu, Xiaoxuan Zhuang, Zhaoyue Wang, Qijin Li
The RFM incorporates a dilated residual block and attention mechanism to expand receptive fields while enhancing sensitivity to spatial information.
no code implementations • 28 Oct 2022 • Chuqin Geng, Nham Le, Xiaojie Xu, Zhaoyue Wang, Arie Gurfinkel, Xujie Si
We show that by using NAP, we can verify a significant region of the input space, while still recalling 84% of the data on MNIST.