Scaling memory-augmented neural networks with sparse reads and writes

J Rae
J Rae
JJ Hunt
JJ Hunt
T Harley
T Harley
AW Senior
AW Senior
G Wayne
G Wayne

neural information processing systems, pp. 3621-3629, 2016.

Cited by: 91|Bibtex|Views114
Other Links: academic.microsoft.com

Abstract:

Neural networks augmented with external memory have the ability to learn algorithmic solutions to complex tasks. These models appear promising for applications such as language modeling and machine translation. However, they scale poorly in both space and time as the amount of memory grows --- limiting their applicability to real-world do...More

Code:

Data:

Your rating :
0

 

Tags
Comments