Hybrid computing using a neural network with dynamic external memory

Malcolm Reynolds
Malcolm Reynolds
Sergio Gómez Colmenarejo
Sergio Gómez Colmenarejo
John Agapiou
John Agapiou
Adrià Puigdomènech Badia
Adrià Puigdomènech Badia

Nature, Volume 538, Issue 7626, 2016, Pages 471-476.

Cited by: 986|Bibtex|Views242|DOI:https://doi.org/10.1038/nature20101
WOS EI
Other Links: pubmed.ncbi.nlm.nih.gov|dblp.uni-trier.de|academic.microsoft.com

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...More

Code:

Data:

Your rating :
0

 

Tags
Comments