English

Better AI through Logical Scaffolding

Machine Learning 2019-09-17 v1 Artificial Intelligence Machine Learning

Abstract

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.

Keywords

Cite

@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

R2 v1 2026-06-23T11:16:07.224Z