原文传递
Leveraging Symbolic Representations for Safe and Assured Learning.
| 题名： | Leveraging Symbolic Representations for Safe and Assured Learning. |
| 作者： | Zutshi, A; Lockett, C; Dietterich, T; Fern, A; Jagannathan, S; Topcu, U; Chaudhuri, S. |
| 摘要： | Report developed under contract FA8750-19-C-0092: Leveraging Symbolic Representations for Safe and Assured Learning.This research effort targets development of novel tools, algorithms and methodologies to improve the assurance ofAutonomous, Learning Enabled Cyber Physical Systems (LE-CPSs). These systems exhibit a rich set of behaviors due tohigher levels of autonomy, and interaction between cyber components and the physical environment. This effort summarizesadvances in symbolic system testing, model extraction, anomaly detection, learning unknown dynamics and formalapproaches to verify these systems. Efforts were integrated within the Controls Systems Analysis Framework and applied toa high fidelity F16 model as the challenge problem. |
| 总页数： | 107 pages |
相关文献
- Scheduling for Urban Air Mobility using Safe Learning.
- Morphodynamic Classification of Coastal Regions Using Deep Learning Through Digital Imagery Collection.
- Development, Deployment, and Assessment of Activity-Based Transportation Courses.
- Certification for Machine Learning.
- MODELING LEARNING AND EVOLUTIONARY ADAPTATION PROCESSES IN ACTIVITY SETTINGS: THEORY AND NUMERICAL SIMULATIONS.
- Hands-On Cybersecurity Studies: Network Diversification with Honeypots.
检索历史
应用推荐
