Hybrid computing using a neural network with dynamic external memory on ShortScience.org

dx.doi.org
sci-hub
scholar.google.com

Hybrid computing using a neural network with dynamic external memory
Alex Graves and Greg Wayne and Malcolm Reynolds and Tim Harley and Ivo Danihelka and Agnieszka Grabska-Barwińska and Sergio Gómez Colmenarejo and Edward Grefenstette and Tiago Ramalho and John Agapiou and Adrià Puigdomènech Badia and Karl Moritz Hermann and Yori Zwols and Georg Ostrovski and Adam Cain and Helen King and Christopher Summerfield and Phil Blunsom and Koray Kavukcuoglu and Demis Hassabis
Nature - 2016 via Local CrossRef
Keywords:

Summaries/Notes 2

[link] Summary by Marek Rei 6 years ago

The DeepMind guys present an extension to the Neural Turing Machine architecture.

https://i.imgur.com/4TC6yAp.png

They call it a Differentiable Neural Computer (DNC) and it uses 1) an attention mechanism to access information in a matrix that acts as a memory, 2) an attention mechanism to save information to that memory, and 3) a transition matrix that stores information about the order in which rows in the memory are modified, in order to better handle sequential information. They test on the bAbI question answering dataset, a graph inference task, and on solving a puzzle of arranging blocks.

Your comment:

Write your summary here (You can use $\LaTeX$ and markdown syntax):

Anon Private