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 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.
- Publication status:
- Published
- Peer review status:
- Peer reviewed
Actions
Access Document
- Files:
-
-
(Preview, Accepted manuscript, pdf, 3.4MB, Terms of use)
-
- Publisher copy:
- 10.1038/nature20101
Authors
Bibliographic Details
- Publisher:
- Nature Publishing Group
- Journal:
- Nature More from this journal
- Volume:
- 538
- Issue:
- 7626
- Pages:
- 471-476
- Publication date:
- 2016-10-12
- Acceptance date:
- 2016-09-19
- DOI:
- EISSN:
-
1476-4687
- ISSN:
-
0028-0836
Item Description
- Language:
-
English
- Pubs id:
-
pubs:653613
- UUID:
-
uuid:dd8473bd-2d70-424d-881b-86d9c9c66b51
- Local pid:
-
pubs:653613
- Source identifiers:
-
653613
- Deposit date:
-
2016-11-10
Terms of use
- Copyright holder:
- Graves et al
- Copyright date:
- 2016
- Notes:
- This is the accepted manuscript version of the article. The final version is available online from Nature at: https://doi.org/10.1038/nature20101
Metrics
If you are the owner of this record, you can report an update to it here: Report update to this record