Search Results for author:
Found 2 papers, 0 papers with code
Incorrect by Construction: Fine Tuning Neural Networks for Guaranteed Performance on Finite Sets of Examples
There is great interest in using formal methods to guarantee the reliability of deep neural networks.
Adaptive Stress Testing: Finding Likely Failure Events with Reinforcement Learning
Finding the most likely path to a set of failure states is important to the analysis of safety-critical systems that operate over a sequence of time steps, such as aircraft collision avoidance systems and autonomous cars.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
