Accueil
Équipe
Publications
Open Source
Démos
Évènements
Blog
Carrières
Nous joindre
Français
Français
English
ServiceNow
ServiceNow recherche
Tags
Machine Learning
ServiceNow recherche
Machine Learning
On the Value of ML Models
We argue that, when establishing and benchmarking Machine Learning (ML) models, the research community should favour evaluation metrics …
Fabio Casati
,
Pierre-André Noël
,
Jie Yang
Workshop at the Neural Information Processing Systems (NeurIPS), 2021.
PDF
Citation
The Variational Bandwidth Bottleneck: Stochastic Evaluation on an Information Budget
In many applications, it is desirable to extract only the relevant information from complex input data, which involves making a …
Anirudh Goyal
,
Yoshua Bengio
,
Matthew Botvinick
,
Sergey Levine
International Conference on Learning Representations (ICLR), 2020.
PDF
Citation
Retrieving Signals in the Frequency Domain with Deep Complex Extractors
Recent advances have made it possible to create deep complex-valued neural networks. Despite this progress, the potential power of …
Chiheb Trabelsi
,
Olexa Bilaniuk
,
Ousmane Amadou Dia
,
Ying Zhang
,
Mirco Ravanelli
,
Jonathan Binas
,
Negar Rostamzadeh
,
Christopher Pal
Workshop at the Neural Information Processing Systems (NeurIPS), 2019.
PDF
Citation
Code
Hinted Networks
We present Hinted Networks: a collection of architectural transformations for improving the accuracies of neural network models for …
Joel Lamy Poirier
,
Anqi Xu
ArXiv, 2018.
PDF
Citation
Data-dependent PAC-Bayes priors via differential privacy
The Probably Approximately Correct (PAC) Bayes framework (McAllester, 1999) can incorporate knowledge about the learning algorithm and …
Gintare Karolina Dziugaite
,
Daniel M. Roy
Conference on Neural Information Processing Systems (NeurIPS), 2018.
PDF
Citation
Improving Explorability in Variational Inference with Annealed Variational Objectives
Despite the advances in the representational capacity of approximate distributions for variational inference, the optimization process …
Chin-Wei Huang
,
Shawn Tan
,
Alexandre Lacoste
,
Aaron Courville
Conference on Neural Information Processing Systems (NeurIPS), 2018.
PDF
Citation
Code
Sparse Attentive Backtracking: Temporal Credit Assignment Through Reminding
Learning long-term dependencies in extended temporal sequences requires credit assignment to events far back in the past. The most …
Nan Rosemary Ke
,
Anirudh Goyal
,
Olexa Bilaniuk
,
Jonathan Binas
,
Christopher Pal
,
Yoshua Bengio
,
Michael C. Mozer
Conference on Neural Information Processing Systems (NeurIPS), 2018.
PDF
Citation
Code
Deep Complex Networks
At present, the vast majority of building blocks, techniques, and architectures for deep learning are based on real-valued operations …
Chiheb Trabelsi
,
Olexa Bilaniuk
,
Ying Zhang
,
Dmitriy Serdyuk
,
Sandeep Subramanian
,
João Felipe Santos
,
Soroush Mehri
,
Negar Rostamzadeh
,
Yoshua Bengio
,
Christopher Pal
International Conference on Learning Representations (ICLR), 2018.
PDF
Citation
Code
Deep Prior
The recent literature on deep learning offers new tools to learn a rich probability distribution over high dimensional data such as …
Alexandre Lacoste
,
Thomas Boquet
,
Negar Rostamzadeh
,
Boris N. Oreshkin
,
Wonchang Chung
,
David Krueger
Workshop at the Neural Information Processing Systems (NeurIPS), 2017.
PDF
Citation
Independently Controllable Factors
It has been postulated that a good representation is one that disentangles the underlying explanatory factors of variation. However, it …
Valentin Thomas
,
Jules Pondard
,
Emmanuel Bengio
,
Marc Sarfati
,
Philippe Beaudoin
,
Marie-Jean Meurs
,
Joelle Pineau
,
Doina Precup
,
Yoshua Bengio
ArXiv, 2017.
PDF
Citation
Citation
×