Communications of the ACM
Surrey Device Takes Us Closer to High-Performing Wearable, Eco-Disposable AI Electronics
University of Surrey researchers developed the Multimodal Transistor to overcome long-standing challenges and perform the same operations as more complex circuits.
Credit: Eve Bestelink et al
Researchers at the University of Surrey in the U.K. have developed the Multimodal Transistor (MMT) to produce efficient analog computation for robotic control, artificial intelligence, and unsupervised machine learning.
The MMT can perform the same operations as more complex circuits, but is immune to the parasitic effects that lower a transistor's capacity to produce uniform repeatable signals, which is a main challenge of traditional "floating gate" designs.
The device allows on/off switching to be controlled independently from the amount of current passing through the structure, allowing it to operate at a higher speed.
Further, this allows the MMT to have a linear dependence between input and output, which is key for ultra-compact digital-to-analog conversion.
The university's Radu Sporea said the MMT "could be the key enabler for future wearables and gadgets beyond the current Internet of Things."
From University of Surrey (U.K.)
View Full Article
Abstracts Copyright © 2020 SmithBucklin, Washington, DC, USA
No entries found