Post Profile






DeepMind’s AI has learned to navigate the Tube using memory

By combining neural networks with external memory, Google’s DeepMind creates a system that can solve tasks like finding the shortest route on a transport map
read more

share

Related Posts


Hybrid computing using a neural network with dynamic external memory

Academics : Nature AOP

A ‘differentiable neural computer’ is introduced that combines the learning capabilities of a neural network with an external memory analogous to the random-access memory in a conventional computer.

Google's Secretive DeepMind Start-up Unveils A "Neural Turing Machine"

Technology : Technology Review Editors' Blog

DeepMind has built a neural network that can access an external memory like a conventional Turing machine. The result is a computer that mimics the short-term memory of the human brain.

Google's Secretive DeepMind Startup Unveils a "Neural Turing Machine"

Technology : Technology Review Editors' Blog

DeepMind has built a neural network that can access an external memory like a conventional Turing machine. The result is a computer that mimics the short-term memory of the human brain.  

Best of 2014: Google's Secretive DeepMind Startup Unveils a "Neural Turing Machine"

Technology : Technology Review Editors' Blog

In October, DeepMind unveiled a neural network that can access an external memory like a conventional Turing machine. The result is a computer that mimics the short-term memory of the human brain.

Artificial Intelligence Navigates The London Underground

News : Newsweek: US

An artificial intelligence algorithm has been developed by Google’s DeepMind that is capable of working out the most efficient way of getting from one point to another on London’s Tube network. The system, known as a differentiable ...

Comments


Copyright © 2016 Regator, LLC