DeepMind AI 'Learns' to Navigate London Tube

...

DeepMind has introduced a new "computer" that uses memories to answer questions and even navigate the London Underground.

The UK-based artificial intelligence firm, owned by Google parent company Alphabet, built a "differentiable neural computer" (DNC), which consults its own memories to acquire and dispense information—much like the human brain.

"We showed how neural networks and memory systems can be combined to make learning machines that can store knowledge quickly and reason about it flexibly," DeepMind researchers Alexander Graves and Greg Wayne wrote in a blog post. "These models … can learn from examples like neural networks, but they can also store complex data like computers."

The DNC, for example, can store a roster of sports players and read out each name individually. It can also process more complicated tasks like deducing ancestral relationships based on a family tree (video above).

The real test, however, is a graph—one of the most complex and general data structures—like the London Underground network. After feeding the computer a layout of the Tube, the machine was able to recall a memory of the map, then answer intricate questions: "Starting at Bond Street and taking the Central line in a direction for one stop, the Circle line in a direction for four stops, and the Jubilee line in a direction for two stops, at what stop do you end up?"

DNC can also plan routes given a query like, "How do you get from Moorgate to Piccadilly Circus?"

"Conventional neural networks in our comparisons either could not store the information, or they could not learn to reason in a way that would generalize to new examples," Graves and Wayne said.

The scientists found they could also train via reinforcement learning: let the computer produce actions but never show it the answer, like the children's game "hot or cold" (video below). In testing, DNC was able to store several subroutines—one per possible goal—in memory and execute one or another.

"The question of how human memory works is ancient and our understanding still developing," the researchers said. "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 organize information into connected facts and use those facts to solve problems."

Categories
GAMES
0 Comment

Leave a Reply

Captcha image


RELATED BY

  • 5300c769af79e

    Business Process Apps for Finance and Purchasing for Dummies

    Download This book explains how automated business workflows and forms help drive efficiency; explores difference finance and purchasing use cases; describes how to build automated, process-based workflows without being a developer; examines how businesses can use a single workflow solution across the entire organization; and provides key criteria to help you evaluate business process apps solutions for your organization.
  • 5300c769af79e

    T-Mobile's New DIGITS is the Latest 1-Number to Rule Them All Idea

    This morning, T-Mobile took the wraps off its latest technology introduction, DIGITS.The idea here is very much Google Voice meets AT&T’s NumberSync in that you get to use a single phone number (your “DIGITS”) across multiple devices and have additional phone numbers funnel through it.
  • 5300c769af79e

    Music Industry Rebounds on Streaming Subscription Surge

    Huge gains in streaming revenue and market share fueled the increase.The biggest contributors were the newly launched paid services from Apple and Tidal, as well as growth in existing services, like Spotify Premium.
  • 5300c769af79e

    10 IoT Startups You Need To Know

    We take a look at 10 IoT startups you need to know because they are doing something a little different or a little special.That's why we're calling this companies you need to know, not companies you should invest in.