Breaking News

Qualcomm Redefining Wireless Audio with Launch of Qualcomm Snapdragon Sound ASUS announces the ROG Strix, TUF Gaming and Dual AMD Radeon RX 6700 XT graphics card series Leica announces The APO-SUMMICRON-M 35 f/2 ASPH GIGABYTE Launches Radeon RX 6700 XT series graphics cards Samsung Announces Galaxy XCover 5, the Newest Durable and Advanced Smartphone Built for Tough Environments

logo

  • Share Us
    • Facebook
    • Twitter
  • Home
  • Home
  • News
  • Reviews
  • Forum
  • Legacy
  • About
    • Submit News

    • Contact Us
    • Privacy

    • Promotion
    • Advertise

    • RSS Feed
    • Site Map

Search form

Google DeepMind Introduces Method for Improving Machine Learning Speed

Google DeepMind Introduces Method for Improving Machine Learning Speed

Enterprise & IT Nov 19,2016 0

Researchers at Google's DeepMind wrote in a paper published online Thursday that they had achieved a leap in the speed and performance of a machine learning system. Deepmind's paper "Reinforcement Learning with Unsupervised Auxiliary Tasks" introduces a method for greatly improving the learning speed and final performance of agents. DeepMind?s new system -- named Unsupervised Reinforcement and Auxiliary Learning agent, or Unreal -- learned to master a three-dimensional maze game called Labyrinth 10 times faster than the existing best AI software. It can now play the game at 87 percent the performance of expert human players, the DeepMind researchers said.

"Our agent is far quicker to train, and requires a lot less experience from the world to train, making it much more data efficient," DeepMind researchers Max Jaderberg and Volodymyr Mnih said. They added that Unreal would allow DeepMind?s researchers to experiment with new ideas much faster because of the reduced time it takes to train the system. DeepMind has already seen its AI products achieve highly respected results teaching itself to play video games, notably the retro Atari title Breakout.

Labyrinth is a game environment that DeepMind developed, loosely based on the design style used by the popular video game series Quake. It involves a machine having to navigate routes through a maze, scoring points by collecting apples.

This style of game is an important area for artificial intelligence research because the chance to score points in the game, and thus reinforce "positive" behaviors, occurs less frequently than in some other games. Additionally, the software has only partial knowledge of the maze?s layout at any one time.

One way the researchers achieved their results was by having Unreal replay its own past attempts at the game, focusing especially on situations in which it had scored points before. The researchers equated this in their paper to the way "animals dream about positively or negatively rewarding events more frequently."

The researchers also helped the system learn faster by asking it to maximize several different criteria at once, not simply its overall score in the game.

DeepMind achieved what is considered a major breakthrough in the field earlier this year when its AlphaGo software beat one of the world?s reigning champions in the ancient strategy game Go.

DeepMind?s Unreal system also mastered 57 vintage Atari games, such as Breakout, much faster -- and achieved higher scores -- than the company?s existing software. The researchers said Unreal could play these games on average 880 percent better than top human players, compared to 853 percent for DeepMind?s older AI agent.

But on the most complex Atari games, such as Montezuma?s Revenge, the new system made bigger leaps in performance.The prior AI system scored zero points, while Unreal achieved 3,000 -- greater than 50 percent of an expert human?s best effort.

Tags: deepmindMachine learning
Previous Post
OLED Makers Seen Struggling To Meet iPhone Output in 2017
Next Post
PS4 Slim Did Not Dethrone Xbox One in October

Related Posts

  • Imec Uses Machine Learning Algorithms in Chip Design to Achieve cm Accuracy and Low-power Ultra Wideband Localization

  • Seagate Uses NVIDIA's AI Inference Tools to Improve Hard Drive Manufacturing

  • Intel and Georgia Tech to Mitigate Machine Learning Deception Attacks

  • DeepMind Researchers Create Deep RL Agent That Outperforms Humans in the Atari Human Benchmark

  • Infineon, Cypress Deal Wins CFIUS Clearance

  • DARPA is Working on Mathematical Framework to Check the Safety of Autonomous Systems

  • IBM Launches New IC922 POWER9-Based Server For ML Inference

  • SiFive and CEVA Partner to Make Machine Learning Processors Mainstream

Latest News

Qualcomm Redefining Wireless Audio with Launch of Qualcomm Snapdragon Sound
Smartphones

Qualcomm Redefining Wireless Audio with Launch of Qualcomm Snapdragon Sound

ASUS announces the ROG Strix, TUF Gaming and Dual AMD Radeon RX 6700 XT graphics card series
GPUs

ASUS announces the ROG Strix, TUF Gaming and Dual AMD Radeon RX 6700 XT graphics card series

Leica announces The APO-SUMMICRON-M 35 f/2 ASPH
Cameras

Leica announces The APO-SUMMICRON-M 35 f/2 ASPH

GIGABYTE Launches Radeon RX 6700 XT series graphics cards
GPUs

GIGABYTE Launches Radeon RX 6700 XT series graphics cards

Samsung Announces Galaxy XCover 5, the Newest Durable and Advanced Smartphone Built for Tough Environments
Smartphones

Samsung Announces Galaxy XCover 5, the Newest Durable and Advanced Smartphone Built for Tough Environments

Popular Reviews

CeBIT 2005

CeBIT 2005

Zidoo Z9S 4K Media Player review

Zidoo Z9S 4K Media Player review

CeBIT 2006

CeBIT 2006

LiteOn iHBS112 review

LiteOn iHBS112 review

Club3D HD3850

Club3D HD3850

Crucial P1 NVMe 1TB SSD review

Crucial P1 NVMe 1TB SSD review

Toshiba Exceria M303 64GB and M501 Exceria Pro 64GB MicroSDXC review

Toshiba Exceria M303 64GB and M501 Exceria Pro 64GB MicroSDXC review

Hitachi DZ-MV100A DVD Camcorder

Hitachi DZ-MV100A DVD Camcorder

  • Home
  • News
  • Reviews
  • Forum
  • Legacy
  • About
    • Submit News

    • Contact Us
    • Privacy

    • Promotion
    • Advertise

    • RSS Feed
    • Site Map
  • About
  • Privacy
  • Contact Us
  • Promotional Opportunities @ CdrInfo.com
  • Advertise on out site
  • Submit your News to our site
  • RSS Feed