Skip to main content

An artificial synapse on a chip is able to learn autonomously

Brain-inspired deep learning neural networks have been behind many of the biggest breakthroughs in artificial intelligence seen over the past 10 years.

But a new research project from the National Center for Scientific Research (CNRS), the University of Bordeaux, and Norwegian information technology company Evry could take that these breakthroughs to next level — thanks to the creation of an artificial synapse on a chip.

Recommended Videos

“There are many breakthroughs from software companies that use algorithms based on artificial neural networks for pattern recognition,” Dr. Vincent Garcia, a CNRS research scientist who worked on the project, told Digital Trends. “However, as these algorithms are simulated on standard processors they require a lot of power. Developing artificial neural networks directly on a chip would make this kind of tasks available to everyone, and much more power efficient.”

Synapses in the brain function as the connections between neurons. Learning takes place when these connections are reinforced, and improved when synapses are stimulated. The newly developed electronic devices (called “memristors”) emulate the behavior of these synapses, by way of a variable resistance that depends on the history of electronic excitations they receive.

“Here we use a specific kind of memristors based on purely electronic effects,” Garcia continued. “In these devices, the active part is a ferroelectric film, which contains electric dipoles, that can be switched with an electric field. Depending on the orientation of these dipoles, the resistance is on or off. In addition, we can control configurations in which domains with up or down dipoles coexist, with intermediate voltage pulses. This gives rise to an analog device with many resistance levels. In our paper, we were able to understand how the resistance of the memristor evolves with voltage pulses and make a model based on the dynamics of ferroelectric domains.”

The result was an array of 45 such memristors which were able to learn to detect simple patterns without any assistance; something referred to as “unsupervised learning” in the machine learning community.

Now that the team is able to predict the behavior of an individual electronic synapse, the next goal is to develop neural networks on a chip that contain hundreds of these ferroelectric memristors. Once this is achieved, they will test it by connecting the neural network to an event-based camera to have a go at detecting moving objects at high-speed.

“The final goal of this project would be to integrate this bio-inspired camera in a car to assist the driver when unexpected objects or persons are crossing the road,” Garcia said.

Should all go according to plan, it may not be long before the neural networks are incorporated as a standard part of the processors found in our smartphones and other mobile devices.

Luke Dormehl
I'm a UK-based tech writer covering Cool Tech at Digital Trends. I've also written for Fast Company, Wired, the Guardian…
Sebastian Stan lays out Bucky’s future after Thunderbolts
Sebastian Stan in Thunderbolts.

There are some spoilers ahead for the ending of Marvel's Thunderbolts. Stop reading now if you don't want to be spoiled.

Earlier this year, Captain America: Brave New World briefly introduced a new direction for James "Bucky" Barnes, a character Sebastian Stan has been playing since 2011 in Captain America: The First Avenger. In Brave New World, the former Winter Soldier apparently retired from being a reformed hero and went into politics by running for Congress. Thunderbolts reveals that Bucky won his election to the House of Representatives. But his stay in Congress was short.

Read more
Jeep Compass EV breaks cover—but will it come to the U.S.?
jeep compass ev us newjeepcompassfirsteditionhawaii  4

Jeep just pulled the wraps off the all-new Compass EV, and while it’s an exciting leap into the electric future, there's a catch—it might not make it to the U.S. anytime soon.
This is a brand new electric version of the Jeep Compass, and being built on Stellantis' STLA platform—the same architecture underpinning models like the Peugeot E-3008 and E-5008—it looks much slicker and packs a lot more inside than previous versions of the Compass.
Let’s start with what’s cool: the new Compass EV is packing up to 404 miles of range on a single charge, a 74 kWh battery, and fast-charging that gets you from 20% to 80% in about 30 minutes. Not bad for a compact SUV with Jeep's badge on the nose.
There are two versions: a front-wheel-drive model with 213 horsepower and a beefier all-wheel-drive version with 375 horsepower. That AWD setup isn’t just for looks—it can handle 20% inclines even without front traction, and comes with extra ground clearance and better off-road angles. In short, it’s still a Jeep.
The design's been refreshed too, and inside you’ll find the kind of tech and comfort you’d expect in a modern EV—sleek, smart, and ready for both city streets and dirt trails.
But here’s the thing: even though production starts soon in Italy, Jeep hasn’t said whether the Compass EV is coming to America. And the signs aren’t promising.
Plans to build it in Canada were recently put on hold, with production now delayed until at least early 2026. Some of that might have to do with possible U.S. tariffs on Canadian and Mexican vehicles—adding a layer of uncertainty to the whole rollout.
According to Kelley Blue Book, a Stellantis spokesperson confirmed that the company has “temporarily paused work on the next-generation Jeep Compass, including activities at” the Canadian plant that was originally meant to build the model. They added that Stellantis is “reassessing its product strategy in North America” to better match customer needs and demand for different powertrain options.
So while Europe and other markets are gearing up to get the Compass EV soon, American drivers might be left waiting—or miss out entirely.
That’s a shame, because on paper, this electric Jeep hits a lot of sweet spots. Let’s just hope it finds a way over here.

Read more
Charlie Cox singles out his least favorite Daredevil: Born Again episode
Charlie Cox in Daredevil: Born Again.

Daredevil: Born Again season 1 was largely reconceived after the 2023 actor and writer strikes. Dario Scardapane -- a veteran of The Punisher series on Netflix -- was brought in to be the new showrunner and he made a lot of changes to the series that were well-received. However, there's one episode that Scardapane didn't really change at all, and it happens to be the least favorite episode of Daredevil: Born Again's leading man, Charlie Cox.

During an appearance on The Playlist, Cox noted that he wasn't very fond of the season's fifth episode, "With Interest," which was a largely standalone episode that featured his character, Matt Murdock, in a bank during a hostage crisis.

Read more