Research

End-to-end information extraction from documents

Document information extraction tasks performed by humans create data consisting of a PDF or document image input, and extracted string outputs.

Autoencoding beyond pixels using a learned similarity metric

We present an autoencoder that leverages learned representations to better measure similarities in data space.

Neural machine translation with characters and hierarchical encoding

Semi-supervised generation with cluster-aware generative models

Deep generative models trained with large amounts of unlabelled data have proven to be powerful within the domain of unsupervised learning.

Auxiliary deep generative models

Deep generative models parameterized by neural networks have achieved state-of-the-art performance in unsupervised and semi-supervised learning.

Hash embeddings for efficient word representations

We present hash embeddings, an efficient method for representing words in a continuous vector form.

Recurrent Relational Networks for Complex Relational Reasoning

Humans possess an ability to abstractly reason about objects and their interactions, an ability not shared with state-of-the-art deep learning models

A disentangled recognition and nonlinear dynamics model for unsupervised learning

This paper takes a step towards temporal reasoning in a dynamically changing video in a latent space.