Guarded Deep Learning using Scenario-based Modeling

Guy Katz

Abstract

Deep neural networks (DNNs) are becoming prevalent, often outperforming manually-created systems. Unfortunately, DNN models are opaque to humans, and may behave in unexpected ways when deployed. One approach for allowing safer deployment of DNN models calls for augmenting them with hand-crafted override rules, which serve to override decisions made by the DNN model when certain criteria are met. Here, we propose to bring together DNNs and the well-studied scenario-based modeling paradigm, by expressing these override rules as simple and intuitive scenarios. This approach can lead to override rules that are comprehensible to humans, but are also sufficiently expressive and powerful to increase the overall safety of the model. We describe how to extend and apply scenario-based modeling to this new setting, and demonstrate our proposed technique on multiple DNN models.

Download


Paper Citation


in Harvard Style

Katz G. (2020). Guarded Deep Learning using Scenario-based Modeling.In Proceedings of the 8th International Conference on Model-Driven Engineering and Software Development - Volume 1: MODELSWARD, ISBN 978-989-758-400-8, pages 126-136. DOI: 10.5220/0009097601260136


in Bibtex Style

@conference{modelsward20,
author={Guy Katz},
title={Guarded Deep Learning using Scenario-based Modeling},
booktitle={Proceedings of the 8th International Conference on Model-Driven Engineering and Software Development - Volume 1: MODELSWARD,},
year={2020},
pages={126-136},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0009097601260136},
isbn={978-989-758-400-8},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 8th International Conference on Model-Driven Engineering and Software Development - Volume 1: MODELSWARD,
TI - Guarded Deep Learning using Scenario-based Modeling
SN - 978-989-758-400-8
AU - Katz G.
PY - 2020
SP - 126
EP - 136
DO - 10.5220/0009097601260136