Skip to main content

Home/ Moxie FutureX/ Group items tagged neural

Rss Feed Group items tagged

Filter: All | Bookmarks | Topics Simple Middle
jrryhdsn

Google's Secretive DeepMind Startup Unveils a "Neural Turing Machine" | MIT Technology ... - 0 views

www.technologyreview.com/...nveils-a-neural-turing-machine

ai neural memory deepmind Neural Turing Machine

shared by jrryhdsn on 04 Nov 14 - No Cached
  • jrryhdsn on 01 Jan 15
     
    "Neural Turing Machine"
piercemcbride

Neural networks can add natural animation to video games - 0 views

www.engadget.com/...s-can-help-animate-video-games

artificial intelligence ai machine learning gaming

shared by piercemcbride on 31 May 17 - No Cached
  • piercemcbride on 31 May 17
     
    "The researchers used machine learning and a neural net to pull animation info from a database, based on what you're doing with the gamepad. "So, instead of storing all the data and selecting which clip to play with, [we] have a system which actually generates animations on the fly, given the user input," the school's Daniel Holden told Ars Technica."
John Rich

From not working to neural networking | The Economist - 0 views

www.economist.com/...ased-old-idea-modern-twist-not

artificial intelligence machine learning deep learning ai

shared by John Rich on 14 Oct 16 - No Cached
  • John Rich on 14 Oct 16
     
    "From not working to neural networking"
piercemcbride

Microsoft's speech recognition engine listens as well as a human - 0 views

www.engadget.com/...ine-listens-as-well-as-a-human

artificial intelligence ai machine learning

shared by piercemcbride on 31 May 17 - No Cached
  • To accomplish the 5.9 percent error rate, which beats a 6.3 percent record set just last month, the Microsoft team leveraged neural language models resembling associative word clouds. That is, a word like "fast" resides much closer to "fast" than it does to "slow". This allowed the speech recognition engine to generalize between words and better recognize them in context.
  • piercemcbride on 31 May 17
     
    "To accomplish the 5.9 percent error rate, which beats a 6.3 percent record set just last month, the Microsoft team leveraged neural language models resembling associative word clouds. That is, a word like "fast" resides much closer to "fast" than it does to "slow". This allowed the speech recognition engine to generalize between words and better recognize them in context. "
1 - 20 of 95 Next › Last »
Showing 20▼ items per page