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.
Start with data to build a better supply chain
Successful digital transformation starts with the right team, an agile mentality, and a strong data foundation, says global digital solutions manager of procurement and supply chain at bp, Raimundo Martinez.
Chiplets: 10 Breakthrough Technologies 2024
Chipmakers are betting that smaller, more specialized chips can extend the life of Moore’s Law.
Quantum computing is taking on its biggest challenge: noise
For a while researchers thought they’d have to make do with noisy, error-prone systems, at least in the near term. That’s starting to change.
Apple Vision Pro: 10 Breakthrough Technologies 2024
Micro-OLED technology has been in development for more than a decade, but the Vision Pro will be the highest-profile demonstration of its abilities to date.
Get the latest updates from
MIT Technology Review
Discover special offers, top stories, upcoming events, and more.