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

    Google's Russian Android Appeal Falls Flat

    A Russian appeals court recently rejected Google's appeal of a US$6.The Ninth Arbitration Appeal Court's ruling, handed down last month, means that the court considered the decision of Russia's Federal Antimonopoly Service to be reasonable and legitimate.
  • 5300c769af79e

    Instagram Adding Translate Button

    There's nothing more frustrating than scrolling past a beautifully filtered photo of breakfast cereal, but not being able to decipher the caption.Captions, comments, and personal details are rendered based on the language settings of the person viewing them.
  • 5300c769af79e

    iOS 10, macOS Sierra Public Betas Released

    The public betas of iOS 10 and macOS Sierra arrived Thursday -- a day after Apple pushed out new betas through its developer channel.Developers have been testing iOS 10 and macOS Sierra for several weeks.
  • 5300c769af79e

    One20 Shifts Social Network For Truckers Into Gear

    Join us for this enlightening webinar where you'll get insight into what to consider when building One20 is a mobile app, navigation specialist, and social network all rolled into a single service specifically for truck drivers.The service allows drivers to connect with one another, plan routes, and save money all at the same time.