Blog

Jul 2, 2024

How Deep Neural Networks Learn Compositional Data: The Random Hierarchy Model

Posted by in category: robotics/AI

Francesco Cagnetta, Leonardo Petrini, Umberto M. Tomasini, Alessandro Favero, and Matthieu Wyart Institute of Physics EPFL, Institute of Electrical Eng.


A hierarchical model of high-dimensional data reveals how deep neural networks leverage their multiple layers to reduce the data dimensionality and learn from a finite set of examples.

Leave a reply