Hybrid computing using a neural network with dynamic external memory
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 machin...
Main Authors: | Graves, A, Wayne, G, Reynolds, M, Harley, T, Danihelka, I, Grabska-Barwińska, A, Colmenarejo, S, Grefenstette, E, Ramalho, T, Agapiou, J, Badia, A, Hermann, K, Zwols, Y, Ostrovski, G, Cain, A, King, H, Summerfield, C, Blunsom, P, Kavukcuoglu, K, Hassabis, D |
---|---|
Formato: | Journal article |
Idioma: | English |
Publicado em: |
Nature Publishing Group
2016
|
Registos relacionados
-
"Not not bad" is not "bad": A distributional account of negation
Por: Hermann, K, et al.
Publicado em: (2013) -
New Directions in Vector Space Models of Meaning
Por: Grefenstette, E, et al.
Publicado em: (2014) -
A Deep Architecture for Semantic Parsing
Por: Grefenstette, E, et al.
Publicado em: (2014) -
Semantic parsing with semi-supervised sequential autoencoders
Por: Kočiský, T, et al.
Publicado em: (2016) -
Neural mechanisms of hierarchical planning in a virtual subway network
Por: Balaguer, J, et al.
Publicado em: (2016)