Skip to main content

Home/ SciByte/ Group items tagged ArtificiaIntelligence

Rss Feed Group items tagged

Filter: All | Bookmarks | Topics Simple Middle
Mars Base

Carnegie Mellon computer searches web 24/7 to analyze images and teach itself common sense - 0 views

phys.org/...-mellon-web-images-common.html

scibyte110 ArtificiaIntelligence

shared by Mars Base on 25 Nov 13 - No Cached
  • NEIL leverages recent advances in computer vision that enable computer programs to identify and label objects in images, to characterize scenes and to recognize attributes, such as colors, lighting and materials, all with a minimum of human supervision
  • since late July and already has analyzed three million images, identifying 1,500 types of objects in half a million images and 1,200 types of scenes in hundreds of thousands of images
  • sometimes, what NEIL finds can surprise even the researchers
  • ...5 more annotations...
  • a search for "apple" might return images of fruit as well as laptop computers
  • team had no idea that a search for F-18 would identify not only images of a fighter jet, but also of F18-class catamarans
  • As its search proceeds, NEIL develops subcategories of objects
  • tricycles can be for kids, for adults and can be motorized, or cars come in a variety of brands and models
  • it begins to notice associations – that zebras tend to be found in savannahs, for instance, and that stock trading floors are typically crowded
Mars Base

New research aims to teach computers common sense - 0 views

phys.org/...2013-11-aims-common.html

scibyte110 ArtificiaIntelligence

shared by Mars Base on 25 Nov 13 - No Cached
  • Researchers are trying to plant a digital seed for artificial intelligence by letting a massive computer system browse millions of pictures and decide for itself what they all mean
  • The system at Carnegie Mellon University is called NEIL, short for Never Ending Image Learning
  • In mid-July, it began searching the Internet for images 24/7 and, in tiny steps, is deciding for itself how those images relate to each other
  • ...13 more annotations...
  • The goal is to recreate what we call common sense—the ability to learn things without being specifically taught
  • NEIL uses advances in computer vision to analyze and identify the shapes and colors in pictures, but it is also slowly discovering connections between objects on its own
  • the computers have figured out that zebras tend to be found in savannahs and that tigers look somewhat like zebras
  • In just over four months, the network of 200 processors has identified 1,500 objects and 1,200 scenes and has connected the dots to make 2,500 associations
  • Some of NEIL's computer-generated associations are wrong
  • "rhino can be a kind of antelope,"
  • "actor can be found in jail cell"
  • "news anchor can look similar to Barack Obama."
  • having a computer make its own associations is an entirely different type of challenge than programming a supercomputer to do one thing very well, or fast
  • humans constantly make decisions using "this huge body of unspoken assumptions," while computers don
  • humans can also quickly respond to some questions that would take a computer longer to figure out
  • "Could a giraffe fit in your car?" she asked. "We'd have an answer, even though we haven't thought about it" in the sense of calculating the giraffe's body mass
  • In the future, NEIL will analyze vast numbers of YouTube videos to look for connections between objects
1 - 3 of 3
Showing 20▼ items per page