← Search

Sandra Fortini

2 accepted papers

2021

Large-width functional asymptotics for deep Gaussian neural networks

ICLR 2021poster

In this paper, we consider fully connected feed-forward deep neural networks where weights and biases are independent and identically distributed according to Gaussian distributions. Extending previous results (Matthews et al., 2018a;b;Yang, 2019) we adopt a function-space perspective, i.e. we look…

Cited by 20SourcePDFScholar
2020

Stable behaviour of infinitely wide deep neural networks

AISTATS 2020poster

We consider fully connected feed-forward deep neural networks (NNs) where weights and biases are independent and identically distributed as symmetric centered stable distributions. Then, we show that the infinite wide limit of the NN, under suitable scaling on the weights, is a stochastic process wh…