Work

Sparsity Regret bounds for XNOR-nets++

Year: 2021
Type: preprint
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
Source: HAL
Language: English
Open Access status: green
OpenAlex ID: W3183327419
Cites: 47
Cited by: 1
Related to: 9