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…)

What do you want to predict, and do you have the data? (more…)

In the context of science, the well-known adage "a picture is worth a thousand words" might well be "a model is worth a thousand datasets." Scientific models, such as Newtonian physics or biological gene regulatory networks, are human-driven simplificatio... (more…)

Contribute to datarevenue-berlin/OpenMLOps development by creating an account on GitHub. (more…)

Neural network makes for smarter-looking avatars, not just smarter enemies... (more…)