Welcome to the Scientific and Industrial Machine Learning Laboratory (SIMLab)

The Scientific and Industrial Machine Learning Laboratory (SIMLab) at HES-SO Valais focuses on developing and applying machine learning (ML) techniques to solve complex problems in close collaboration with both academic and industrial partners.

We have a strong emphasis on practical applications and ensuring the real-world impact of our research.

Core Areas

We specialize in several key areas of machine learning and data science:

• Differential Programming: we heavily rely on general differentiable programs, enabling the integration of domain knowledge and complex structures into learning models using JAX and Flax.
• Advanced Data Processing: we specialize in handling large-scale and complex datasets using state-of-the-art technologies and methodologies, such as Polars, scaling data processing pipelines to very large-scale datasets.
• Hybrid Modeling: using differential programming methods, we combine data-driven approaches with traditional simulations to leverage the strengths of both methodologies, resulting in more accurate and reliable predictions.
• Uncertainty Quantification: developing techniques to assess and manage uncertainty in machine learning models, enhancing their robustness and reliability in real-world.
• Dynamical Systems: developing methods for analyzing, modelling, and forecasting complex dynamical systems, with applications in energy and environmental monitoring. Tools: Diffrax, Optax.
• Explainable AI (XAI): we develop machine learning models that are transparent and interpretable, allowing users to understand and trust the decisions made by these models. Tools: SHAP.