RAISSE

Four conceptual priorities

• Development of interpretable, robust analytical AI tools for system diagnostics, prediction and control, subject to low-cost constraints for the machine learning (ML) model
• Determination of smarter hardware configurations in engineering, sensor or measurement devices using ML analytics
• Integration of engineering and/or domain-specific expert knowledge into the design of AI systems to achieve lower complexity and, consequently, less demanding hardware requirements for running an ML-powered diagnostic and control engineering system  
• Transfer of information or data from well-defined and controlled settings to new environments using reliable machine learning models
   

Challenges and requirements for machine learning models 

• ML models with low computational complexity, specifically tailored to the application or task
• ML models that can be trained using perhaps a small amount of data
• ML models with mathematical guarantees regarding convergence and model/decision robustness
• Interpretable ML models for comprehensible model inspection and decision/prediction control = white-box ML