Skip to Content
Computing

A new artificial synapse is faster and more efficient than ones in your brain

January 29, 2018

Biologically inspired circuitry could help build future low-power AI chips—if some obstacles are overcome.

The news: Researchers at the US National Institute of Standards and Technology built a new magnetically controlled electronic synapse, an artificial equivalent of the ones that link neurons. They fire millions of times faster than the ones in your brain, while using 1,000th as much energy (which is also less than any other artificial synapse to date).

Why it matters: Synthetic synapses, which gather multiple signals and fire electronic pulses at a threshold, may be an alternative to transistors in regular processors. They can be assembled to create so-called neuromorphic chips that work more like a brain. Such devices can run artificial neural networks, which underpin modern AI, more efficiently than regular chips. This new synapse could make them even more energy-efficient.

But: The synapses haven’t yet been used to create a large device, so it’s not clear a useful chip can be built from them. And they run at temperatures of 5 K—too cold for a practical computing device.

Deep Dive

Computing

Inside the hunt for new physics at the world’s largest particle collider

The Large Hadron Collider hasn’t seen any new particles since the discovery of the Higgs boson in 2012. Here’s what researchers are trying to do about it.

Why China is betting big on chiplets

By connecting several less-advanced chips into one, Chinese companies could circumvent the sanctions set by the US government.

How Wi-Fi sensing became usable tech

After a decade of obscurity, the technology is being used to track people’s movements.

VR headsets can be hacked with an Inception-style attack

Stay connected

Illustration by Rose Wong

Get the latest updates from
MIT Technology Review

Discover special offers, top stories, upcoming events, and more.

Thank you for submitting your email!

Explore more newsletters

It looks like something went wrong.

We’re having trouble saving your preferences. Try refreshing this page and updating them one more time. If you continue to get this message, reach out to us at customer-service@technologyreview.com with a list of newsletters you’d like to receive.