We've updated our Privacy Policy to make it clearer how we use your personal data.

We use cookies to provide you with a better experience, read our Cookie Policy

Identifying Artificial Intelligence “Blind Spots”

News   Jan 28, 2019 | Original Press Release from MIT

 
Identifying Artificial Intelligence “Blind Spots”

A model by MIT and Microsoft researchers identifies instances where autonomous cars have “learned” from training examples that don’t match what’s actually happening on the road, which can be used to identify which learned actions could cause real-world errors. Credit: MIT News

 
 
 

RELATED ARTICLES

Fruit Fly Wings May Help Genetic Medicine Take Off

News

How do fruit flies grow their wings? Scientists discovered a surprising answer that could one day help diagnose and treat human genetic diseases.

READ MORE

New Insights Into Alcohol and Tobacco Use

News

A recent study using data from 1.2 million people has discovered several genes associated with an increased use of alcohol and tobacco.

READ MORE

Putting Data Privacy in the Hands of Users

News

A new platform ensures that web services adhere to users’ preferences on how their data are stored and shared in the cloud. In a paper being presented at this week’s USENIX Networked Systems Design and Implementation conference, the researchers behind the platform, called Riverbed, show how it forces data center servers to only use data in ways that users explicitly approve.

READ MORE

 

To personalize the content you see on Technology Networks homepage, Log In or Subscribe for Free

LOGIN SUBSCRIBE FOR FREE