Safety Assurance for Systems with Machine Learning Components

Authors

  • Chelsea Sidrane Stanford University

Keywords:

Safety, Verification, Neural Networks, Bayesian Learning, Testing, Deep Learning, Machine Learning, Formal Methods, Reinforcement Learning, Validation, AI Safety

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.

Downloads

Published

2021-05-18

How to Cite

Sidrane, C. (2021). Safety Assurance for Systems with Machine Learning Components. Proceedings of the AAAI Conference on Artificial Intelligence, 35(18), 15734-15735. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/17864

Issue

Section

The Twenty-Sixth AAAI/SIGAI Doctoral Consortium