BROWSE TOPICS

RESOURCES

ABOUT THIS SITE

 

In a Big Network of Computers, Evidence of Machine Learning

Jim Wilson/The New York Times There Google scientists created one of the largest neural networks for machine learning by connecting 16,000 computer processors, which they turned loose on the Internet to learn on its own. Although some of the computer science ideas that the researchers are using are not new, the sheer scale of the software simulations is leading to learning systems that were not previously possible. And Google researchers are not alone in exploiting the techniques, which are referred to as deep learning models. Last year Microsoft scientists presented research showing that the techniques could be applied equally well to build computer systems to understand human speech.

Author: Publication Date: Crawl Date: Source: Topic: Contributor: Type: Language: Format:
June 25, 2012 July 01, 2012 www.nytimes.com (User submitted) Applications CognitiveScience MachineLearning Vision NewsFinder Text English HTML

Whitelist words:

  1. neural network: 4 occurrences
  2. machin learn: 2 occurrences
  3. speech recognit: 2 occurrences
  4. machin vision: 1 occurrence

Categorization (need >= 0.5 to match):

  1. AIOverview: 0.273678
  2. Agents: 0.0461138
  3. Applications: 0.756449
  4. CognitiveScience: 0.945174
  5. Education: 0.00109565
  6. Ethics: 0.00483629
  7. Games: 0.00563209
  8. History: 0.190102
  9. Interfaces: 0.0245381
  10. MachineLearning: 0.956618
  11. NaturalLanguage: 0.0825411
  12. Philosophy: 0.0054713
  13. Reasoning: 0.0362643
  14. Representation: 0.00271844
  15. Robots: 0.00820945
  16. ScienceFiction: 0.000231739
  17. Speech: 0.281558
  18. Systems: 0.0764862
  19. Vision: 0.776651

Duplicates (threshold=0.17):

  1. (sim=0.456) 9183: Google's Simulated Human Brain Has Trained Itself to Recognize Cats on YouTube
  2. (sim=1.000) 9203: How Many Computers to Identify a Cat? 16000
  3. (sim=0.262) 9206: How Google Is Teaching Computers to See
  4. (sim=0.368) 9233: Using large-scale brain simulations for machine learning and AI
  5. (sim=0.431) 9247: Google neural network teaches itself to identify cats
  6. (sim=0.278) 9248: A Neural Network Learns What A Face Is
  7. (sim=0.301) 9249: Google computer works out how to spot cats
  8. (sim=0.481) 9250: Google builds a neural network that can identify a cat
  9. (sim=0.329) 9251: Google X's Neural Network Could Indicate Future Of Search
  10. (sim=0.429) 9252: Google Creates Learning Brain, Turns It Loose On The Internet
  11. (sim=0.280) 9253: AI System Learns to Recognize Faces and Felines

Transcript:

  1. Preferred over duplicates
  2. Published
Collections:
brokenlinkform:brokenlink
AAAI   Recent Changes   Edit   History   Print   Contact Us
Page last modified on July 02, 2012, at 12:00 AM