Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

Sparsity Regret bounds for XNOR-nets++

Abstract : Despite the attractive qualities of convolutional neural networks (CNNs), and the universality of architectures emerging now, CNNs are still prohibitive regarding environmental impact due to electric consumption or carbon footprint, as well as deployment in constrained platform such as microcomputers. We address this problem and sketch how PAC-Bayesian theory can be applied to learn lighter
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03262679
Contributor : Sébastien Loustau <>
Submitted on : Wednesday, June 16, 2021 - 4:38:26 PM
Last modification on : Tuesday, June 22, 2021 - 3:53:38 AM

File

Sparsity_Regret_bounds_for_Xno...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03262679, version 1

Citation

Andrew Chee, Sébastien Loustau. Sparsity Regret bounds for XNOR-nets++. 2021. ⟨hal-03262679v1⟩

Share

Metrics

Record views

14

Files downloads

1