activity
20172021
most citedPopulation Based Training of Neural Networks

249 citations · 393 across the 5 of their papers we have counts for

collaborators

7 papers

cs.CV202125 cited

Predicting Video with VQVAE

Jacob Walker, Ali Razavi, Aäron van den Oord

In recent years, the task of video prediction-forecasting future video given past video frames-has attracted attention in the research community. In this paper we propose a novel a…

cs.LG20201 cited

Do Transformers Need Deep Long-Range Memory

Jack W. Rae, Ali Razavi

Deep attention models have advanced the modelling of sequential data across many domains. For language modelling in particular, the Transformer-XL -- a Transformer augmented with a…

cs.LG2019105 cited

Generating Diverse High-Fidelity Images with VQ-VAE-2

Ali Razavi, Aaron van den Oord, Oriol Vinyals

We explore the use of Vector Quantized Variational AutoEncoder (VQ-VAE) models for large scale image generation. To this end, we scale and enhance the autoregressive priors used in…

cs.CV2019

Data-Efficient Image Recognition with Contrastive Predictive Coding

Olivier J. Hénaff, Aravind Srinivas, Jeffrey De Fauw +4

Human observers can learn to recognize new categories of images from a handful of examples, yet doing so with artificial ones remains an open challenge. We hypothesize that data-ef…

cs.LG201913 cited

Preventing Posterior Collapse with delta-VAEs

Ali Razavi, Aäron van den Oord, Ben Poole +1

Due to the phenomenon of "posterior collapse," current latent variable generative models pose a challenging design choice that either weakens the capacity of the decoder or require…

cs.NE2018

Hyperbolic Attention Networks

Caglar Gulcehre, Misha Denil, Mateusz Malinowski +8

We introduce hyperbolic attention networks to endow neural networks with enough capacity to match the complexity of data with hierarchical and power-law structure. A few recent app…