Riemannian metrics for neural networks I: Feedforward networks - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles Information and Inference Year : 2015

Riemannian metrics for neural networks I: Feedforward networks

Abstract

We describe four algorithms for neural network training, each adapted to different scalability constraints. These algorithms are mathematically principled and invariant under a number of transformations in data and network representation, from which performance is thus independent. These algorithms are obtained from the setting of differential geometry, and are based on either the natural gradient using the Fisher information matrix, or on Hessian methods, scaled down in a specific way to allow for scalability while keeping some of their key mathematical properties.

Dates and versions

hal-00857982 , version 1 (04-09-2013)

Identifiers

Cite

Yann Ollivier. Riemannian metrics for neural networks I: Feedforward networks. Information and Inference, 2015, 4 (2), pp.108-153. ⟨10.1093/imaiai/iav006⟩. ⟨hal-00857982⟩
324 View
0 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More