Journal article icon

Journal article

Hybrid computing using a neural network with dynamic external memory

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 i...

Expand abstract
Publication status:
Published
Peer review status:
Peer reviewed
Version:
Accepted Manuscript

Actions


Access Document


Files:
Publisher copy:
10.1038/nature20101

Authors


Reynolds, M More by this author
Danihelka, I More by this author
Expand authors...
Publisher:
Nature Publishing Group Publisher's website
Journal:
Nature Journal website
Volume:
538
Issue:
7626
Pages:
471-476
Publication date:
2016-10-12
DOI:
EISSN:
1476-4687
ISSN:
0028-0836
Pubs id:
pubs:653613
URN:
uri:dd8473bd-2d70-424d-881b-86d9c9c66b51
UUID:
uuid:dd8473bd-2d70-424d-881b-86d9c9c66b51
Local pid:
pubs:653613
Language:
English

Terms of use


Metrics



If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP