Hybrid computing using a neural network with dynamic external memory

Alex Graves

doi:10.1038/nature20101

Return

Hybrid computing using a neural network with dynamic external memory

2016-10-12

1.0K

PRE

Agnieszka Grabska‐Barwińska

Sergio Gómez Colmenarejo

Edward Grefenstette

Tiago Ramalho

John Agapiou

Adrià Puigdomènech Badia

Christopher Summerfield

Phil Blunsom

Koray Kavukcuoglu

Demis Hassabis *

DOI：10.1038/nature20101

Original

Original request for help

Save

Abstract

En 中文

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 machine learning model called a differentiable neural computer (DNC), which consists of a neural network that can read from and write to an external memory matrix, analogous to the random-access memory in a conventional computer. Like a conventional computer, it can use its memory to represent and manipulate complex data structures, but, like a neural network, it can learn to do so from data. When trained with supervised learning, we demonstrate that a DNC can successfully answer synthetic questions designed to emulate reasoning and inference problems in natural language. We show that it can learn tasks such as finding the shortest path between specified points and inferring the missing links in randomly generated graphs, and then generalize these tasks to specific graphs such as transport networks and family trees. When trained with reinforcement learning, a DNC can complete a moving blocks puzzle in which changing goals are specified by sequences of symbols. Taken together, our results demonstrate that DNCs have the capacity to solve complex, structured tasks that are inaccessible to neural networks without external read-write memory.

Keywords:

COMPLEMENTARY LEARNING-SYSTEMS

HIPPOCAMPUS

MODELS

AI Summary

Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.