Enhancing Deep Learning with Scenario-Based Override Rules: A Case Study

Adiel Ashrov, Guy Katz

2023

Abstract

Deep neural networks (DNNs) have become a crucial instrument in the software development toolkit, due to their ability to efficiently solve complex problems. Nevertheless, DNNs are highly opaque, and can behave in an unexpected manner when they encounter unfamiliar input. One promising approach for addressing this challenge is by extending DNN-based systems with hand-crafted override rules, which override the DNN’s output when certain conditions are met. Here, we advocate crafting such override rules using the well-studied scenario-based modeling paradigm, which produces rules that are simple, extensible, and powerful enough to ensure the safety of the DNN, while also rendering the system more translucent. We report on two extensive case studies, which demonstrate the feasibility of the approach; and through them, propose an extension to scenario-based modeling, which facilitates its integration with DNN components. We regard this work as a step towards creating safer and more reliable DNN-based systems and models.

Paper Citation

in Harvard Style

Ashrov A. and Katz G. (2023). Enhancing Deep Learning with Scenario-Based Override Rules: A Case Study. In Proceedings of the 11th International Conference on Model-Based Software and Systems Engineering - Volume 1: MODELSWARD, ISBN 978-989-758-633-0, pages 253-268. DOI: 10.5220/0011796600003402

in Bibtex Style

@conference{modelsward23,
author={Adiel Ashrov and Guy Katz},
title={Enhancing Deep Learning with Scenario-Based Override Rules: A Case Study},
booktitle={Proceedings of the 11th International Conference on Model-Based Software and Systems Engineering - Volume 1: MODELSWARD,},
year={2023},
pages={253-268},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011796600003402},
isbn={978-989-758-633-0},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 11th International Conference on Model-Based Software and Systems Engineering - Volume 1: MODELSWARD,
TI - Enhancing Deep Learning with Scenario-Based Override Rules: A Case Study
SN - 978-989-758-633-0
AU - Ashrov A.
AU - Katz G.
PY - 2023
SP - 253
EP - 268
DO - 10.5220/0011796600003402