Copy
Creative stuff, weekly collection
<<First Name>>, here is your copy.

View this email in your browser

Hybrid chips can run AI on battery-powered devices


In traditional electronics, separate chips process and store data, wasting energy as they toss data back and forth over what engineers call a “memory wall.” New algorithms combine several energy-efficient hybrid chips to create the illusion of one mega–AI chip.

 

Smartwatches and other battery-powered electronics would be even smarter if they could run AI algorithms. But efforts to build AI-capable chips for mobile devices have so far hit a wall – the so-called “memory wall” that separates data processing and memory chips that must work together to meet the massive and continually growing computational demands imposed by AI.

 

Hardware and software innovations give eight chips the illusion that they’re one mega-chip working together to run AI. “Transactions between processors and memory can consume 95 percent of the energy needed to do machine learning and AI, and that severely limits battery life,” said computer scientist Subhasish Mitra, senior author of a new study published in Nature Electronics.

 

Now, a team that includes Stanford computer scientist Mary Wootters and electrical engineer H.-S. Philip Wong has designed a system that can run AI tasks faster, and with less energy, by harnessing eight hybrid chips, each with its own data processor built right next to its own memory storage. This recent paper builds on the team’s prior development of a new memory technology, called RRAM, that stores data even when power is switched off – like flash memory – only faster and more energy efficiently. Their RRAM advance enabled the Stanford researchers to develop an earlier generation of hybrid chips that worked alone.

 

Their latest design incorporates a critical new element: algorithms that meld the eight, separate hybrid chips into one energy-efficient AI-processing engine.

Read the full article at: news.stanford.edu

The post Hybrid chips can run AI on battery-powered devices appeared first on Antonios Bouris.


Read in browser »
share on Twitter Like Hybrid chips can run AI on battery-powered devices on Facebook

Neanderthals disappeared from Europe earlier than thought, study suggests


Neanderthal fossils from a cave in Belgium believed to belong to the last survivors of their species ever discovered in Europe are thousands of years older than once thought, a new study said.

 

Previous radiocarbon dating of the remains from the Spy Cave yielded ages as recent as approximately 24,000 years ago, but the new testing pushes the clock back to between 44,200 to 40,600 years ago. The research appeared in the Proceedings of the National Academy of Sciences and was carried out by a team from Belgium, Britain and Germany.

 

Read the full article at: phys.org

The post Neanderthals disappeared from Europe earlier than thought, study suggests appeared first on Antonios Bouris.


Read in browser »
share on Twitter Like Neanderthals disappeared from Europe earlier than thought, study suggests on Facebook

Robotic ‘Skin’ Could Allow Machines and Prosthetics to Feel | IE


A global research team used magnetic sensors and a flexible magnetized film as skin. Read how here.

Read the full article at: interestingengineering.com

The post Robotic ‘Skin’ Could Allow Machines and Prosthetics to Feel | IE appeared first on Antonios Bouris.


Read in browser »
share on Twitter Like Robotic ‘Skin’ Could Allow Machines and Prosthetics to Feel | IE on Facebook


 

Recent Articles:

Mammoth Genomes Shatter Record for Oldest Isolated DNA Sequences
Precision Genome Editing Enters the Modern Era: Can We Cure Genetic Diseases by Rewriting DNA?
NASA’s Mars Helicopter Ingenuity Reports to Home Base
How Denmark’s energy island could make history
Facebook Blocks News in Australia Over Law Forcing It to Pay for News
Copyright © 2021 @Design Thinking, All rights reserved.


unsubscribe from this list    update subscription preferences 

Email Marketing Powered by Mailchimp
Email
Email
Website
Website
Facebook
Facebook
Twitter
Twitter
LinkedIn
LinkedIn
Instagram
Instagram
Tumblr
Tumblr
Pinterest
Pinterest
YouTube
YouTube