Skip to yearly menu bar Skip to main content


Interpretable Meta-Learning of Physical Systems

Matthieu Blanke · marc lelarge

Halle B #29
[ ] [ Project Page ]
Wed 8 May 7:30 a.m. PDT — 9:30 a.m. PDT


Machine learning methods can be a valuable aid in the scientific process, but they need to face challenging settings where data come from inhomogeneous experimental conditions. Recent meta-learning methods have made significant progress in multi-task learning, but they rely on black-box neural networks, resulting in high computational costs and limited interpretability. We introduce CAMEL, a new meta-learning architecture capable of learning efficiently from multiple environments, with an affine structure with respect to the learning task. We prove that CAMEL can identify the physical parameters of the system, enabling interpreable learning. We demonstrate the competitive generalization performance and the low computational cost of our method by comparing it to state-of-the-art algorithms on physical systems, ranging from toy models to complex, non-analytical systems. The interpretability of our method is illustrated with original applications to parameter identification and to adaptive control and system identification.

Chat is not available.