Thrusts
The workshop will be comprised of three thrusts.
Knowledge informed AI: This thrust focuses on the technical challenges associated with developing robust digital models, including but not limited to:
- Integrating physics or other knowledge into machine learning
- Methods for multi-scale prediction (especially multi-scale time-series prediction)
- Control of physical systems with assistance of learned AI models
Assurance: This thrust focuses on the technical challenges associated with assuring robustness of digital twins and includes:
- Uncertainty quantification
- Verification, validation, and calibration
- Assurance, including causal inference, explainability, and interpretability
- Security and resilience
- Detecting and dealing with bias
Co-design Ecosystem: This thrust focuses on the practical challenges when using digital twins, such as:
- Edge deployment for real-time and power-efficient deployment of digital twins
- Federated learning for privacy or for data reduction
- Integrating HPC and edge systems, including model and data management
- Online and offline continuous learning on edge-based systems
- Human-machine interface design
- Interoperability and standardization
Click HERE to view the workshop info sheet.
