Skip to Main content Skip to Navigation
Poster communications

Dichotomize and Generalize: PAC-Bayesian Binary Activated Deep Neural Networks

Gaël Letarte 1 Pascal Germain 2 Benjamin Guedj 3, 4, 5, 6, 7 François Laviolette 8
2 SIERRA - Statistical Machine Learning and Parsimony
DI-ENS - Département d'informatique de l'École normale supérieure, CNRS - Centre National de la Recherche Scientifique, Inria de Paris
6 MODAL - MOdel for Data Analysis and Learning
Inria Lille - Nord Europe, LPP - Laboratoire Paul Painlevé - UMR 8524, METRICS - Evaluation des technologies de santé et des pratiques médicales - ULR 2694, Polytech Lille - École polytechnique universitaire de Lille, Université de Lille, Sciences et Technologies
Complete list of metadata

https://hal.inria.fr/hal-02482354
Contributor : Benjamin Guedj <>
Submitted on : Tuesday, February 18, 2020 - 8:03:58 AM
Last modification on : Tuesday, May 4, 2021 - 2:06:02 PM
Long-term archiving on: : Tuesday, May 19, 2020 - 12:33:28 PM

File

42-PBGNet_poster.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02482354, version 1

Collections

Citation

Gaël Letarte, Pascal Germain, Benjamin Guedj, François Laviolette. Dichotomize and Generalize: PAC-Bayesian Binary Activated Deep Neural Networks. ML with guarantees -- NeurIPS 2019 workshop, Dec 2019, Vancouver, Canada. ⟨hal-02482354⟩

Share

Metrics

Record views

9723

Files downloads

430