We present an approach for designing correct-by-construction neural networks (and other machine learning models) that are guaranteed to be consistent with a collection of input-output specifications before, during, and after algorithm training. Our method involves designing a constrained predictor for each set of compatible constraints, and combining them safely via a convex combination of their predictions. We demonstrate our approach on synthetic datasets and an aircraft collision avoidance problem.
@article{arxiv.2001.11062,
title = {Safe Predictors for Enforcing Input-Output Specifications},
author = {Stephen Mell and Olivia Brown and Justin Goodwin and Sung-Hyun Son},
journal= {arXiv preprint arXiv:2001.11062},
year = {2020}
}
Comments
10 pages, 5 figures, paper accepted to the NeurIPS 2019 Workshop on Machine Learning with Guarantees and the NeurIPS 2019 Workshop on Safety and Robustness in Decision Making