Anything-in anything-out: A new modular AI model

Researchers at EPFL have developed a new, uniquely modular machine learning model for flexible decision-making. It is able to input any mode of text, video, image, sound, and time-series and then output any number, or combination, of predictions.

ai model combination computer sciences decision epfl image machine machine learning machine learning model making modular modular ai predictions researchers series sound text video