NELL, the self-teaching artificial intelligence at Carnegie Mellon, has a Twitter account and knows how to use it
Posted 10.14.2010 at 12:31 pm
7 Comments
NELL's Twitter Feed
For the last 10 months, Carnegie Mellon University’s Never-Ending Language Learning System, or NELL, has been continuously searching the web for text patterns and grouping them into different semantic categories, a system that closely mimics the way humans learn. But NELL has adopted another human behavior as well: tweeting everything she does.
When she learns a new fact, NELL adds it to her online database, and tweets her discoveries, so you can follow her progress. For example, today she learned that the phrase “dem franchise boys” fits in the category of “music artist.” NELL’s knowledge base currently consists of around 440,000 facts, with around 87 percent accuracy. Many of her tweeted lessons demonstrate amazing analytical capabilities – she was able to get “tool” from “Anchor Fixing Self Tapping Screw Bolts.” The New York Times recently published an in-depth look at exactly how NELL learns these things.
NELL isn’t perfect though. And thank goodness, because that means we get some pretty adorable not-quite-there-yet tweets, such as: “I think "chicken recipe time" is a #condiment” and “I think "anonymously" is a #fish.” NELL’s followers can tweet corrections to her and help her improve her associations. Check out her feed or browse her whole knowledge database to see more.
7 Comments
To comment, please Login.
Popular Tags
Technology
|
|
|
|
|
|
July 2013: The Future Of Flight
The incredible innovations, like drone swarms and perpetual flight, bringing aviation into the world of tomorrow. Plus: today's greatest sci-fi writers predict the future, the science behind the summer's biggest blockbusters, a Doctor Who-themed DIY 'bot, the organs you can do without, and much more.
.jpg)
Popular on Popsci
Most Commented
Technology
- Green Light For Plan To Build World's Tallest Building At Record Speed
- Why The U.S. Won't Dare Kill Edward Snowden With A Drone Strike
- U.S. Government Uses Early Knowledge Of Microsoft Bugs For Spying
- Congress Was Not Really Briefed On PRISM
- A Concise History Of The NSA's Online Spying Program PRISM
- Who's More Powerful, China Or The United States? [Infographic]
- Why Government Phone Spying Is Really About Big Data
- Watch This Insane Helicopter-Bike Fly Around
- Designers Spruce Up The Government's Crappy PowerPoint
- Laser Time Cloak Hides The Fact That An Event Ever Happened
Most Emailed
Technology
- A Brief History Of The Demise Of Battle Bots
- Nursing Home Tracks Residents' Every Move
- Researchers Can Now "Hear" The Exact Shape Of A Room
- Designers Make City Noise Actually Sound Good
- All Of America's Waterways On One Map [Infographic]
- The 6 Most Important Things We Learned From Edward Snowden's Guardian Q&A
- Stanford's Artificial Neural Network Is The Biggest Ever
- New DNA Fog Covers Crime-Scene Suspects With Evidence
- Meet NASA's Astronaut Class of 2013
- Meet NASA's Astronaut Class Of 2013
Most Viewed
Technology
- A Brief History Of The Demise Of Battle Bots
- Nursing Home Tracks Residents' Every Move
- Researchers Can Now "Hear" The Exact Shape Of A Room
- Designers Make City Noise Actually Sound Good
- All Of America's Waterways On One Map [Infographic]
- The 6 Most Important Things We Learned From Edward Snowden's Guardian Q&A
- Stanford's Artificial Neural Network Is The Biggest Ever
- New DNA Fog Covers Crime-Scene Suspects With Evidence
- Meet NASA's Astronaut Class Of 2013
- Meet NASA's Astronaut Class of 2013
Online Content Director: Suzanne LaBarre | Email
Senior Editor: Paul Adams | Email
Associate Editor: Dan Nosowitz | Email
Assistant Editor: Colin Lecher | Email
Assistant Editor: Rose Pastore | Email
Contributing Writers:
Kelsey D. Atherton | Email
Francie Diep | Email
Shaunacy Ferro | Email
Today on PopSci.com
.JPG)
Copyright © 2012 Popular Science
A Bonnier Corporation Company. All rights reserved. Reproduction in whole or in part without permission is prohibited.
I think it would get more out of facebook.
agreed
By saying that NELL has "adopted" the human behaviour of tweeting you are misleading the reader. It is more likely that the software was specifically progremmed to do so and therefore has "adopted" no "human behavior". FAIL.
I'm curious about that statement too Tom91. It would be a great deal more startling if NELL "figured out" not only semantic categorization but set up "her" own Twitter account. SKYNET IS AWARE!!!
How can I tweet corrections to it? I found a few mistakes (like thinking that 'thick' is a colour), but there's very little info on how to rectify this.
@Gringo.Frenzy
I think that the researchers are calling all the tweet update shots ... otherwise they might get a hundred tweets come in making the bot think "A Boombox is not a toy."