We describe the concept of logical scaffolds, which can be used to improve the quality of software that relies on AI components. We explain how some of the existing ideas on runtime monitors for perception systems can be seen as a specific instance of logical scaffolds. Furthermore, we describe how logical scaffolds may be useful for improving AI programs beyond perception systems, to include general prediction systems and agent behavior models.
@article{arxiv.1909.06965,
title = {Better AI through Logical Scaffolding},
author = {Nikos Arechiga and Jonathan DeCastro and Soonho Kong and Karen Leung},
journal= {arXiv preprint arXiv:1909.06965},
year = {2019}
}
Comments
CAV Workshop on Formal Methods for ML-enabled Autonomous Systems 2019