ML models often exhibit unexpectedly poor behavior when they are deployed in real-world domains. We identify underspecification as a key reason for these failures. An ML pipeline is underspecified when it can return many predictors with equivalently stron... (more…)

Analyzing design patterns that help ML collect signal. (more…)

A machine learning algorithm for auto-discovering conserved quantities has been tested on five Hamiltonian systems, including the gravitational 3-body problem. (more…)

When flooding occurs, Synthetic Aperture Radar (SAR) imagery is often used to identify flood extent and the affected buildings for two reasons: (i) for early disaster response, such as rescue operations, and (ii) for flood risk analysis. Furthermore, the ... (more…)

To learn more and make your own visit: https://g.co/tinysorter Tiny Sorter is a fun starter project that teaches you about machine learning and physical comp... (more…)