Neural Networks Regularization Through Class-wise Invariant Representation Learning - Normandie Université Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2019

Neural Networks Regularization Through Class-wise Invariant Representation Learning

Résumé

Training deep neural networks is known to require a large number of training samples. However, in many applications only few training samples are available. In this work, we tackle the issue of training neural networks for classification task when few training samples are available. We attempt to solve this issue by proposing a new regularization term that constrains the hidden layers of a network to learn class-wise invariant representations. In our regularization framework, learning invariant representations is generalized to the class membership where samples with the same class should have the same representation. Numerical experiments over MNIST and its variants showed that our proposal helps improving the generalization of neural network particularly when trained with few samples. We provide the source code of our framework https://github.com/sbelharbi/learning-class-invariant-features .

Dates et versions

hal-02129472 , version 1 (14-05-2019)

Identifiants

Citer

Soufiane Belharbi, Clement Chatelain, Romain Hérault, Sébastien Adam. Neural Networks Regularization Through Class-wise Invariant Representation Learning. 2019. ⟨hal-02129472⟩
25 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More