Safety Assurance for Systems with Machine Learning Components

Abstract

The use of machine learning components in safety-critical systems creates reliability concerns. My thesis focuses on developing algorithms to address these concerns. Because the assurance of a safety-critical system generally requires multiple types of validation, my research takes three directions: safe deep learning algorithms, formal verification of neural networks, and adaptive testing methods.

Cite

Text

Sidrane. "Safety Assurance for Systems with Machine Learning Components." AAAI Conference on Artificial Intelligence, 2021. doi:10.1609/AAAI.V35I18.17864

Markdown

[Sidrane. "Safety Assurance for Systems with Machine Learning Components." AAAI Conference on Artificial Intelligence, 2021.](https://mlanthology.org/aaai/2021/sidrane2021aaai-safety/) doi:10.1609/AAAI.V35I18.17864

BibTeX

@inproceedings{sidrane2021aaai-safety,
  title     = {{Safety Assurance for Systems with Machine Learning Components}},
  author    = {Sidrane, Chelsea},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2021},
  pages     = {15734-15735},
  doi       = {10.1609/AAAI.V35I18.17864},
  url       = {https://mlanthology.org/aaai/2021/sidrane2021aaai-safety/}
}