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...
Hlavní autoři: | 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 |
---|---|
Médium: | Journal article |
Jazyk: | English |
Vydáno: |
Nature Publishing Group
2016
|
Podobné jednotky
-
"Not not bad" is not "bad": A distributional account of negation
Autor: Hermann, K, a další
Vydáno: (2013) -
New Directions in Vector Space Models of Meaning
Autor: Grefenstette, E, a další
Vydáno: (2014) -
A Deep Architecture for Semantic Parsing
Autor: Grefenstette, E, a další
Vydáno: (2014) -
Semantic parsing with semi-supervised sequential autoencoders
Autor: Kočiský, T, a další
Vydáno: (2016) -
Neural mechanisms of hierarchical planning in a virtual subway network
Autor: Balaguer, J, a další
Vydáno: (2016)