Engineers build LEGO-like AI chip that could reduce electronics waste

The MIT design uses light, instead of physical wires, to transmit information through the chip.

 Illustrative image of AI.  (photo credit: PIXABAY)
Illustrative image of AI.
(photo credit: PIXABAY)

Engineers at Massachusetts Institute of Technology (MIT) have built a LEGO-like artificial intelligence (AI) chip, with their sight on sustainable, modular electronics. The team’s results were published Monday in peer-reviewed Nature Electronics.

The researchers dubbed the LEGO-like chip a "reconfigurable" AI chip because it has vast expandability. They say it can keep devices up to date while reducing the population's electronic waste.  The design uses light, instead of physical wires, to transmit information through the chip and layers can be swapped out or stacked on, such as to add new sensors or updated processors.

"You can add as many computing layers and sensors as you want, such as for light, pressure, and even smell.”

MIT postdoc Jihoon Kang

This chip is stacked with three image recognition blocks, each composed of an image sensor, optical communication layer, and artificial synapse array for classifying one of three letters, M, I, or T. 

 The sign at Building 76 at the Massachusetts Institute of Technology (MIT) in Cambridge, Massachusetts, US, November 21, 2018 (credit: BRIAN SNYDER/REUTERS)
The sign at Building 76 at the Massachusetts Institute of Technology (MIT) in Cambridge, Massachusetts, US, November 21, 2018 (credit: BRIAN SNYDER/REUTERS)

"Unlimited expandability" 

“You can add as many computing layers and sensors as you want, such as for light, pressure, and even smell,” said MIT postdoc Jihoon Kang. “We call this a LEGO-like reconfigurable AI chip because it has unlimited expandability depending on the combination of layers.”

Added Jeehwan Kim, associate professor of mechanical engineering at MIT: “As we enter the era of the internet of things based on sensor networks, demand for multifunctioning edge-computing devices will expand dramatically. Our proposed hardware architecture will provide high versatility of edge computing in the future.” 

The engineers said they plan to add more sensing and processing capabilities to the chip, including layers to a cellphone’s camera so it could recognize more complex images. They envision the applications to be endless.