activity
20142024
most citedDeep Speech 2: End-to-End Speech Recognition in English and Mandarin

2.2k citations · 3.1k across the 17 of their papers we have counts for

collaborators
Showing 2014Show all

3 papers · 1 filter

stat.ML2014★ 18 cited

Deep Directed Generative Autoencoders

Sherjil Ozair, Yoshua Bengio

For discrete data, the likelihood can be rewritten exactly and parametrized into if has enough capacity to put no pro…

stat.ML2014★ 3 cited

On the Equivalence Between Deep NADE and Generative Stochastic Networks

Li Yao, Sherjil Ozair, Kyunghyun Cho +1

Neural Autoregressive Distribution Estimators (NADEs) have recently been shown as successful alternatives for modeling high dimensional multimodal distributions. One issue associat…

cs.LG2014★ 8 cited

Multimodal Transitions for Generative Stochastic Networks

Sherjil Ozair, Li Yao, Yoshua Bengio

Generative Stochastic Networks (GSNs) have been recently introduced as an alternative to traditional probabilistic modeling: instead of parametrizing the data distribution directly…