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.
Original language | English |
---|---|
Title of host publication | MODELSWARD 2020 - Proceedings of the 8th International Conference on Model-Driven Engineering and Software Development |
Editors | Bran Selić |
Publisher | Science and Technology Publications, Lda |
Pages | 126-136 |
Number of pages | 11 |
ISBN (Print) | 9789897584008 |
DOIs | |
State | Published - 2020 |
Event | 8th International Conference on Model-Driven Engineering and Software Development , MODELSWARD 2020 - Valletta, Malta Duration: 25 Feb 2020 → 27 Feb 2020 |
Publication series
Name | International Conference on Model-Driven Engineering and Software Development |
---|---|
ISSN (Electronic) | 2184-4348 |
Conference
Conference | 8th International Conference on Model-Driven Engineering and Software Development , MODELSWARD 2020 |
---|---|
Country/Territory | Malta |
City | Valletta |
Period | 25/02/20 → 27/02/20 |
Bibliographical note
Publisher Copyright:© 2022 by SCITEPRESS – Science and Technology Publications, Lda. All rights reserved.
Keywords
- Behavioral Programming
- Deep Neural Networks
- Machine Learning
- Scenario-based Modeling