Connect with us

Science

Artificial Intelligence Neural Network Learns When It Should Not Be Trusted – SciTechDaily

A faster way to estimate uncertainty in AI-assisted decision-making could lead to safer outcomes. Increasingly, artificial intelligence systems known as deep learning…

Published

on

post featured image

MIT researchers have developed a way for deep learning neural networks to rapidly estimate confidence levels in their output. The advance could enhance safety and efficiency in AI-assisted decision making. Credit: MIT
A faster way to estimate uncertainty in AI-assisted decision-making could lead to safer outcomes.
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…

Click here to view the original article.

You might also like ...

Find out how we’re working toward living and working in space at TC Sessions: Space 2020 – TechCrunch
Scientists identify deep-sea blob as new species using only video – The Guardian
post featured image
Caribbean coral reefs under threat from aggressive algae – Loop News Cayman