Site de Vincent Gripon

Blog sur mes recherches et mon enseignement

Compression of Deep Neural Networks on the Fly

G. Soulié, V. Gripon et M. Robert, "Compression of Deep Neural Networks on the Fly," dans Lecture Notes in Computer Science, Volume 9887, pp. 153--170, septembre 2016.

Thanks to their state-of-the-art performance, deep neural networks are increasingly used for object recognition. To achieve the best results, they use millions of parameters to be trained. However, when targetting embedded applications the size of these models becomes problematic. As a consequence, their usage on smartphones or other resource limited devices is prohibited. In this paper we introduce a novel compression method for deep neural networks that is performed during the learning phase. It consists in adding an extra regularization term to the cost function of fully-connected layers. We combine this method with Product Quantization (PQ) of the trained weights for higher savings in storage consumption. We evaluate our method on two data sets (MNIST and CIFAR10), on which we achieve significantly larger compression rates than state-of-the-art methods.

Télécharger le manuscrit.

Bibtex
@article{SouGriRob20169,
  author = {Guillaume Soulié and Vincent Gripon and
Maëlys Robert},
  title = {Compression of Deep Neural Networks on the
Fly},
  journal = {Lecture Notes in Computer Science},
  year = {2016},
  volume = {9887},
  pages = {153--170},
  month = {September},
}




Vous êtes le 795837ème visiteur

Site de Vincent Gripon