Improved Geometric Path Enumeration for Verifying ReLU Neural Networks
2020
Neural networks provide quick approximations to complex functions, and have been increasingly used in perception as well as control tasks. For use in mission-critical and safety-critical applications, however, it is important to be able to analyze what a neural network can and cannot do. For feed-forward neural networks with ReLU activation functions, although exact analysis is NP-complete, recently-proposed verification methods can sometimes succeed.
- Correction
- Source
- Cite
- Save
- Machine Reading By IdeaReader
28
References
29
Citations
NaN
KQI