Researchers from MIT found a way to create neural networks that are 90% smaller but just as smart.
In a new paper, researchers from MIT’s Computer Science and Artificial Intelligence Lab (CSAIL) have shown that neural networks contain subnetworks that are up to one-tenth the size yet capable of being trained to make equally accurate predictions — and sometimes can learn to do so even faster than the originals.
This article stood out to me because if neural networks can be smaller but just as smart, maybe it could encourage companies to keep machine learning locally on a device, like Apple does.
In 1999, MIT created a puzzle designed to take 35 years to solve. Belgian programmer Bernard Fabrot has solved it early.
The puzzle essentially involves doing roughly 80 trillion successive squarings of a starting number, and was specifically designed to foil anyone trying to solve it more quickly by using parallel computing.
“There have been hardware and software advances beyond what I predicted in 1999,” says MIT professor Ron Rivest, who first announced the puzzle in April 1999. “The puzzle’s fundamental challenge of doing roughly 80 trillion squarings remains unbroken, but the resources required to do a single squaring have been reduced by much more than I predicted.”
MIT has developed a smart mask that can alter your mind. It can make you horny or anxious by listening to your own breathing via feedback mechanisms. The device, called Masque, was created by artist and recent graduate of MIT Media Lab Xin Liu. In Ms. Liu’s thesis, she describes how Masque “caused wearers to feel more stressed and more sexually aroused, despite no registered change in their physiology.” She worked with industrial designer Hongxin Zhang to create it. It hides the electronics inside of its curved frame, with a temperature sensor placed underneath the wearer’s nose. Who knows? Maybe some day in the future you’ll find the Masque in your local sex shop.