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...
Autori principali: | 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 |
---|---|
Natura: | Journal article |
Lingua: | English |
Pubblicazione: |
Nature Publishing Group
2016
|
Documenti analoghi
Documenti analoghi
-
"Not not bad" is not "bad": A distributional account of negation
di: Hermann, K, et al.
Pubblicazione: (2013) -
New Directions in Vector Space Models of Meaning
di: Grefenstette, E, et al.
Pubblicazione: (2014) -
A Deep Architecture for Semantic Parsing
di: Grefenstette, E, et al.
Pubblicazione: (2014) -
Semantic parsing with semi-supervised sequential autoencoders
di: Kočiský, T, et al.
Pubblicazione: (2016) -
Neural mechanisms of hierarchical planning in a virtual subway network
di: Balaguer, J, et al.
Pubblicazione: (2016)