Robustness evaluation of deep neural networks with provable guarantees
<p>This thesis presents methodologies to guarantee the robustness of deep neural networks, thus facilitating the deployment of deep learning techniques in safety-critical real-world systems. We study the maximum safe radius of a network with respect to an input, such that all the points within...
主要作者: | Wu, M |
---|---|
其他作者: | Kwiatkowska, M |
格式: | Thesis |
語言: | English |
出版: |
2020
|
主題: |
相似書籍
-
Global robustness evaluation of deep neural networks with provable guarantees for the Hamming distance
由: Ruan, W, et al.
出版: (2019) -
Training-free neural active learning with initialization robustness guarantees
由: Singh, Jasraj
出版: (2023) -
Safety verification for deep neural networks with provable guarantees
由: Kwiatkowska, M
出版: (2019) -
Reachability analysis of deep neural networks with provable guarantees
由: Ruan, W, et al.
出版: (2018) -
Safety and robustness for deep learning with provable guarantees (keynote)
由: Kwiatkowska, M
出版: (2019)