Alexander Scheinker

Alexander is the Adaptive Machine Learning Team Leader in the Applied Electrodynamics Group at Los Alamos National Laboratory.

He has been extending the capability of state-of-the-art machine learning (ML) methods to handle time-varying systems by developing novel adaptive and physics-constrained ML algorithms which incorporate real-time feedback and hard physics constraints within ML architectures.

While standard ML tools fail for time-varying systems or systems with distribution shift, unless some sort of brute force re-training is applied, adaptive ML methods incorporate feedback to adapt in an un-supervised way and remain accurate far beyond the span of the training data by incorporating physics constraints.