Timezone: »

 
Poster
Relational recurrent neural networks
Adam Santoro · Ryan Faulkner · David Raposo · Jack Rae · Mike Chrzanowski · Theophane Weber · Daan Wierstra · Oriol Vinyals · Razvan Pascanu · Timothy Lillicrap

Tue Dec 04 07:45 AM -- 09:45 AM (PST) @ Room 210 #88
in Tue Poster Session A »

Memory-based neural networks model temporal data by leveraging an ability to remember information for long periods. It is unclear, however, whether they also have an ability to perform complex relational reasoning with the information they remember. Here, we first confirm our intuitions that standard memory architectures may struggle at tasks that heavily involve an understanding of the ways in which entities are connected -- i.e., tasks involving relational reasoning. We then improve upon these deficits by using a new memory module -- a Relational Memory Core (RMC) -- which employs multi-head dot product attention to allow memories to interact. Finally, we test the RMC on a suite of tasks that may profit from more capable relational reasoning across sequential information, and show large gains in RL domains (BoxWorld & Mini PacMan), program evaluation, and language modeling, achieving state-of-the-art results on the WikiText-103, Project Gutenberg, and GigaWord datasets.

Keywords: Recurrent Networks · Memory-Augmented Neural Networks
[ Paper] 

Author Information

Adam Santoro (DeepMind)
Ryan Faulkner (Deepmind)
David Raposo (DeepMind)
Jack Rae (DeepMind, UCL)
Mike Chrzanowski (DeepMind)
Theophane Weber (DeepMind)
Daan Wierstra (DeepMind Technologies)
Oriol Vinyals (Google DeepMind)

Oriol Vinyals is a Research Scientist at Google. He works in deep learning with the Google Brain team. Oriol holds a Ph.D. in EECS from University of California, Berkeley, and a Masters degree from University of California, San Diego. He is a recipient of the 2011 Microsoft Research PhD Fellowship. He was an early adopter of the new deep learning wave at Berkeley, and in his thesis he focused on non-convex optimization and recurrent neural networks. At Google Brain he continues working on his areas of interest, which include artificial intelligence, with particular emphasis on machine learning, language, and vision.

Razvan Pascanu (Google DeepMind)
Timothy Lillicrap (Google DeepMind)

More from the Same Authors