Deepmind - Dnc

txt


We introduced a form of memory-augmented neural network called a differentiable neural computer (DNC), and demonstrated that it can learn to use its memory to answer questions about complex, structured data.

Hybrid computing using a neural network with dynamic external memory In a study published in Nature in October 2016, we introduced a form of memory-augmented neural network called a differentiable neural computer (DNC), and demonstrated that it can learn to use its memory to answer questions about complex, structured data, including artificially generated stories, family trees, and even a map of the London Underground. The DNC code is available on DeepMind's GitHub repository here. Neural networks excel at pattern recognition and quick, reactive decision-making, but we are only just beginning to build neural networks that can think slowly – that is, deliberate or reason using knowledge. We show how neural networks and memory systems can be combined to make learning machines that can store knowledge quickly and reason about it flexibly. These models, which we call differentiable neural computers (DNCs), can learn from examples like neural networks, but they can also store complex data like computers. When we designed DNCs, we wanted machines that could learn to form and navigate complex data structures on their own. At the heart of a DNC is a neural network called a controller, which is analogous to the processor in a computer. A controller is responsible for taking input in, reading from and writing to memory, and producing output that can be interpreted as an answer. Differentiable neural computers learn how to use memory and how to produce answers completely from scratch. They learn to do so using the magic of optimisation: when a DNC produces an answer, we compare the answer to a desired correct answer. Over time, the controller learns to produce answers that are closer and closer to the correct answer. In the process, it figures out how to use its memory. We hope that DNCs provide both a new tool for computer science and a new metaphor for cognitive science and neuroscience: here is a learning machine that, without prior programming, can organise information into connected facts and use those facts to solve problems.

Learn more at deepmind.com


Login to Leave A Comment
About The Company
Deepmind
  • Research
  • 3 Products
  • 4 Case Studies

DeepMind is the world leader in artificial intelligence research and its application for positive impact.

Discover, Learn and Evaluate AI Companies and Solutions

Save content to your library

Save case studies, articles, blog posts and more. Curate your research library with content directly from AI companies.

Login with LinkedIn Login with Twitter

Sign in with Email

The latest updates from AI companies in your industry

Get a weekly newsletter with the latest posts directly from the AI companies. Follow companies to tailor your feed.

LATEST | POPULAR
JEDAI PRODUCT SUITE

Anagog provides a solution suite that offers to mobile app owners the most cost-effective, end-to-end, customer engagement solution.

SPELL - HYPERPARAMETER SEARCHES

Optimize hyperparameters to improve the accuracy of your model with the Spell Hyper command

SPELL - JUPYTER NOTEBOOK SERVER - GPU POWERED

Collaborative Jupyter Notebook or JupyterLab workspace server with powerful GPUs

SPELL - DEEP LEARNING PLATFORM

The fastest and most powerful end-to-end platform for machine learning and deep learning.

INZATA ANALYTICS

AI-Powered Analytics Software for Any Data

CLUEY TRAVEL

Discover your perfect travel destination

EXXACT DEEP LEARNING WORKSTATIONS AND SERVERS

DEEP LEARNING NVIDIA GPU SOLUTIONS: Accelerate your AI research today.

BIZON G5000

Deep Learning Workstation

BIZON G7000

Deep Learning Rackmount Server

AMAZON SAGEMAKER

Machine learning for every developer and data scientist.

Make sure your business and career keeps up with the changing world.
Sign up