Understanding Local Robustness of Deep Neural Networks under Natural Variations
2021
Deep Neural Networks (DNNs) are being deployed in a wide range of settings today, from safety-critical applications like autonomous driving to commercial applications involving image classifications. However, recent research has shown that DNNs can be brittle to even slight variations of the input data. Therefore, rigorous testing of DNNs has gained widespread attention.
Keywords:
- Correction
- Source
- Cite
- Save
- Machine Reading By IdeaReader
82
References
4
Citations
NaN
KQI