Hybrid computing using a neural network with dynamic external memory

Alex Graves (), Greg Wayne (), Malcolm Reynolds, Tim Harley, Ivo Danihelka, Agnieszka Grabska-Barwińska, Sergio Gómez Colmenarejo, Edward Grefenstette, Tiago Ramalho, John Agapiou, Adrià Puigdomènech Badia, Karl Moritz Hermann, Yori Zwols, Georg Ostrovski, Adam Cain, Helen King, Christopher Summerfield, Phil Blunsom, Koray Kavukcuoglu and Demis Hassabis
Additional contact information
Alex Graves: Google DeepMind
Greg Wayne: Google DeepMind
Malcolm Reynolds: Google DeepMind
Tim Harley: Google DeepMind
Ivo Danihelka: Google DeepMind
Agnieszka Grabska-Barwińska: Google DeepMind
Sergio Gómez Colmenarejo: Google DeepMind
Edward Grefenstette: Google DeepMind
Tiago Ramalho: Google DeepMind
John Agapiou: Google DeepMind
Adrià Puigdomènech Badia: Google DeepMind
Karl Moritz Hermann: Google DeepMind
Yori Zwols: Google DeepMind
Georg Ostrovski: Google DeepMind
Adam Cain: Google DeepMind
Helen King: Google DeepMind
Christopher Summerfield: Google DeepMind
Phil Blunsom: Google DeepMind
Koray Kavukcuoglu: Google DeepMind
Demis Hassabis: Google DeepMind

Nature, 2016, vol. 538, issue 7626, 471-476

Abstract: Abstract Artificial neural networks are remarkably adept at sensory processing, sequence learning and reinforcement learning, but are limited in their ability to represent variables and data structures and to store data over long timescales, owing to the lack of an external memory. Here we introduce a machine learning model called a differentiable neural computer (DNC), which consists of a neural network that can read from and write to an external memory matrix, analogous to the random-access memory in a conventional computer. Like a conventional computer, it can use its memory to represent and manipulate complex data structures, but, like a neural network, it can learn to do so from data. When trained with supervised learning, we demonstrate that a DNC can successfully answer synthetic questions designed to emulate reasoning and inference problems in natural language. We show that it can learn tasks such as finding the shortest path between specified points and inferring the missing links in randomly generated graphs, and then generalize these tasks to specific graphs such as transport networks and family trees. When trained with reinforcement learning, a DNC can complete a moving blocks puzzle in which changing goals are specified by sequences of symbols. Taken together, our results demonstrate that DNCs have the capacity to solve complex, structured tasks that are inaccessible to neural networks without external read–write memory.

Date: 2016
References: Add references at CitEc
Citations: View citations in EconPapers (7)

Downloads: (external link)
https://www.nature.com/articles/nature20101 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:nature:v:538:y:2016:i:7626:d:10.1038_nature20101

Ordering information: This journal article can be ordered from
https://www.nature.com/

DOI: 10.1038/nature20101

Access Statistics for this article

Nature is currently edited by Magdalena Skipper

More articles in Nature from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().