4 papers
Generalization performance of narrow one-hidden layer networks in the teacher-student setting
Rodrigo Pérez Ortiz, Gibbs Nwemadji, Jean Barbier +4
Understanding the generalization properties of neural networks on simple input-output distributions is key to explaining their performance on real datasets. The classical teacher-s…
Random Features Hopfield Networks generalize retrieval to previously unseen examples
Silvio Kalaj, Clarissa Lauditi, Gabriele Perugini +3
It has been recently shown that a learning transition happens when a Hopfield Network stores examples generated as superpositions of random features, where new attractors correspon…
Instantons in Theories: Transseries, Virial Theorems and Numerical Aspects
Ludovico T. Giorgini, Ulrich D. Jentschura, Enrico M. Malatesta +2
We discuss numerical aspects of instantons in two- and three-dimensional theories with an internal symmetry group, the so-called -vector model. Combining asymptoti…
Properties of the geometry of solutions and capacity of multi-layer neural networks with Rectified Linear Units activations
Carlo Baldassi, Enrico M. Malatesta, Riccardo Zecchina
Rectified Linear Units (ReLU) have become the main model for the neural units in current deep learning systems. This choice has been originally suggested as a way to compensate for…