Light-Driven All-in-One Chip Could Dramatically Improve Edge AI Performance, Efficiency
Brain-inspired chip handles imaging, memory, and even AI processing, and is being positioned as a breakthrough in neurobotics.
Researchers at RMIT University, Colorado State University, Northeast Normal University, and the University of California have designed a multifunction computer chip which combines imaging, processing, memory, and machine learning into a single device — and runs on light.
"Our new technology radically boosts efficiency and accuracy by bringing multiple components and functionalities into a single platform," claims lead researcher Associate Professor Sumeet Walia of the project. "It’s getting us closer to an all-in-one AI device inspired by nature’s greatest computing innovation — the human brain."
"Our aim is to replicate a core feature of how the brain learns, through imprinting vision as memory. The prototype we’ve developed is a major leap forward towards neurorobotics, better technologies for human-machine interaction and scalable bionic systems. Imagine a dash cam in a car that’s integrated with our neuro-inspired hardware – this means it can recognise lights, signs, objects and make instant decisions, without having to connect to the internet. By bringing it all together into one chip, we can deliver unprecedented levels of efficiency and speed in autonomous and AI-driven decision-making."
Based on black phosphorous, the ultra-thin chip changes its electrical resistance based on exposure to different light wavelengths. By shining different colours of light onto its surface, the researchers are able to carry out different tasks — from capturing an image to using the chip as memory, as well as on-chip AI processing.
"By packing so much core functionality into one compact nanoscale device, we can broaden the horizons for machine learning and AI to be integrated into smaller applications," notes lead author Dr. Taimur Ahmed. "Using our chip with artificial retinas, for example, would enable scientists to miniaturize that emerging technology and improve accuracy of the bionic eye. Our prototype is a significant advance towards the ultimate in electronics: A brain-on-a-chip that can learn from its environment just like we do."
The team's work has been published under closed-access terms in the journal Advanced Materials.