A neural network learns when it should not be trusted - A faster way to estimate uncertainty in AI-assisted decision-making could lead to safer outcomes

Title:

A neural network learns when it should not be trusted

 

Author:

Daniel Ackerman

 

Published:

MIT News, 20 November 2020

https://news.mit.edu/2020/neural-network-uncertainty-1120

 

From the article:

Increasingly, artificial intelligence systems known as deep learning neural networks are used to inform decisions vital to human health and safety, such as in autonomous driving or medical diagnosis. These networks are good at recognizing patterns in large, complex datasets to aid in decision-making. But how do we know they’re correct? Alexander Amini and his colleagues at MIT and Harvard University wanted to find out.