Skip to content
aiqbench takeChips & Infra

aiqbench analysis

MIT researchers have developed 2nm nanoscale devices that mimic neuron firing using viscoelastic polymers to store information mechanically, potentially enabling low-power computing architectures. This approach integrates storage and processing within the material itself, addressing adhesion challenges in mechanical computing while offering new pathways for efficient hardware design. The technology represents a significant step toward bio-inspired computing platforms that could power next-generation wearable devices and specialized AI accelerators.
Sources coveringQuantum Zeitgeist, techradar.com
What this isA model's reading of the article and related coverage, written for aiqbench. Not the publisher's words.

MIT builds nanoscale devices that mimic neuron firing

Quantum Zeitgeist6 min read

MIT engineers built devices, 2nm in size, that mimic how neurons fire, potentially enabling more efficient computing.

MIT researchers have built a chip containing hundreds of nanoscale devices, each with a viscoelastic polymer layer measuring just 2 nanometers. These devices mimic neuron firing through reconfigurable motion, potentially leading to more efficient computing platforms. The technology minimizes components by integrating computing functions into the material itself, opening opportunities for low-power applications like wearable health devices. “Complex and coupled nanoscale phenomena can provide tremendous opportunities for new approaches to information processing,” says Farnaz Niroui, an associate professor at MIT and senior author of the research. Featuring a 2-nanometer layer of polydimethylsiloxane (PDMS), a viscoelastic polymer, the core of the new nanoscale devices dictates how they process information through…

Excerpt shown under the publisher's RSS terms · 109 words · full text and figures are on the publisher's site

Related coverage