Riemannian metrics for neural networks I: Feedforward networks

Yann Ollivier 1, 2
2 TAO - Machine Learning and Optimisation
CNRS - Centre National de la Recherche Scientifique : UMR8623, Inria Saclay - Ile de France, UP11 - Université Paris-Sud - Paris 11, LRI - Laboratoire de Recherche en Informatique
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.
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-00857982
Contributeur : Yann Ollivier <>
Soumis le : mercredi 4 septembre 2013 - 13:33:38
Dernière modification le : jeudi 5 avril 2018 - 12:30:12

Lien texte intégral

Identifiants

Citation

Yann Ollivier. Riemannian metrics for neural networks I: Feedforward networks. Information and Inference, Oxford University Press (OUP), 2015, 4 (2), pp.108-153. 〈http://imaiai.oxfordjournals.org/content/4/2/108〉. 〈10.1093/imaiai/iav006〉. 〈hal-00857982〉

Partager

Métriques

Consultations de la notice

497