Fast Training of Provably Robust Neural Networks by SingleProp
Main Authors: | Boopathy, Akhilan, Weng, Lily, Liu, Sijia, Chen, Pin-Yu, Zhang, Gaoyuan, Daniel, Luca, Intelligence, Assoc Advancement Artificial |
---|---|
Other Authors: | Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science |
Format: | Article |
Language: | English |
Published: |
2022
|
Online Access: | https://hdl.handle.net/1721.1/143109 |
Similar Items
-
CNN-Cert: An Efficient Framework for Certifying Robustness of Convolutional Neural Networks
by: Boopathy, Akhilan, et al.
Published: (2021) -
Robustness to training disturbances in SpikeProp Learning
by: Shrestha, Sumit Bam, et al.
Published: (2020) -
Towards More Generalizable Neural Networks via Modularity
by: Boopathy, Akhilan
Published: (2022) -
Nutri-bullets: Summarizing Health Studies by Composing Segments
by: Shah, Darsh J, et al.
Published: (2022) -
Scalable and Safe Multi-Agent Motion Planning with Nonlinear Dynamics and Bounded Disturbances
by: Chen, Jingkai, et al.
Published: (2022)