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

Advertisement

Cutting Down the Huge Carbon Footprint of Neural Network Training

News   May 19, 2020 | Original story from Rice University

 
Cutting Down the Huge Carbon Footprint of Neural Network Training

Rice University's Early Bird method for training deep neural networks finds key connectivity patterns early in training, reducing the computations and carbon footprint for the increasingly popular form of artificial intelligence known as deep learning. Credit: Y. Lin/Rice University

 
 
Advertisement
 

RELATED ARTICLES

Exploring the Evolution of the Human Brain at the Single-cell Level

News

A team of scientists led by Philip Khaitovich, a professor at the Skoltech Center for Life Sciences, has conducted a large-scale analysis of gene expression in 33 different regions of human, chimpanzee, macaque and bonobo brains, adopting a mixture of bulk RNA seq and sNuc-Seq.

READ MORE

Silicon "Neurons" Could Help Processors Do More With Less

News

When it fires, a neuron consumes significantly more energy than an equivalent computer operation. And yet, a network of coupled neurons can perform complex tasks at energy levels that are currently unattainable for even state-of-the-art processors. What does a neuron do to save energy that a contemporary computer processing unit doesn't? New research could have the answer.

READ MORE

Identifying the Brain Regions Linked to Facial Recognition

News

Using "sub-millimeter" brain implants, researchers at The University of Texas Health Science Center at Houston (UTHealth), have been able to determine which parts of the brain are linked to facial and scene recognition.

READ MORE

 

Like what you just read? You can find similar content on the communities below.

Neuroscience

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

LOGIN SUBSCRIBE FOR FREE