no code implementations • 15 May 2024 • Simmaco Di Lillo, Domenico Marinucci, Michele Salvi, Stefano Vigogna
In this paper, we propose to use the angular power spectrum of the limiting field to characterize the complexity of the network architecture.
no code implementations • 12 Jul 2023 • Stefano Favaro, Boris Hanin, Domenico Marinucci, Ivan Nourdin, Giovanni Peccati
We study the distribution of a fully connected neural network with random Gaussian weights and biases in which the hidden layer widths are proportional to a large constant $n$.
no code implementations • 29 Jun 2023 • Valentina Cammarota, Domenico Marinucci, Michele Salvi, Stefano Vigogna
We prove a Quantitative Functional Central Limit Theorem for one-hidden-layer neural networks with generic activation function.