10.8k citations
- Université de MontréalCA18 papers
- Centre National de la Recherche ScientifiqueFR9 papers
- McGill UniversityCA8 papers
- Sorbonne UniversitéFR7 papers
- Université Paris-SaclayFR7 papers
- École de Technologie SupérieureCA6 papers
- National Tsing Hua UniversityTW6 papers
- University College LondonGB6 papers
- University of CambridgeGB6 papers
- University of ChicagoUS6 papers
- University of TrentoIT6 papers
- Alcatel Lucent (Germany)DE5 papers
5 papers · 1 filter
Online Estimation of Multiple Dynamic Graphs in Pattern Sequences
Jimmy Gaudreault, Arunabh Saxena, Hideaki Shimazaki
Sequences of correlated binary patterns can represent many time-series data including text, movies, and biological signals. These patterns may be described by weighted combinations…
Z-Forcing: Training Stochastic Recurrent Networks
Anirudh Goyal, Alessandro Sordoni, Marc-Alexandre Côté +2
Many efforts have been devoted to training generative latent variable models with autoregressive decoders, such as recurrent neural networks (RNN). Stochastic recurrent models have…
A Closer Look at Memorization in Deep Networks
Devansh Arpit, Stanisław Jastrzębski, Nicolas Ballas +8
We examine the role of memorization in deep learning, drawing connections to capacity, generalization, and adversarial robustness. While deep networks are capable of memorizing noi…
Unimodal probability distributions for deep ordinal classification
Christopher Beckham, Christopher Pal
Probability distributions produced by the cross-entropy loss for ordinal classification problems can possess undesired properties. We propose a straightforward technique to constra…
Exponentially Increasing the Capacity-to-Computation Ratio for Conditional Computation in Deep Learning
Kyunghyun Cho, Yoshua Bengio
Many state-of-the-art results obtained with deep networks are achieved with the largest models that could be trained, and if more computation power was available, we might be able…