Researchers at Los Alamos National Laboratory in the US discovered that neural networks reap benefits when exposed to an artificial analogue of sleep.
Yijing Watkins, a computer scientist at Los Alamos, said, “We were interested by the prospect of training a neuromorphic processor in a manner analogous to how humans and other biological systems learn from their environment throughout youth development”
It is said that the discovery was made while working on a form of artificial intelligence designed to mimic how humans learn to see.
The AI became unstable during long periods of unsupervised learning, as it attempted to classify objects using their dictionary definitions without having any prior examples to compare them to.
Researchers then exposed AI to a state that is similar to what a human brain experiences during sleep and the neural network’s stability was restored
A paper detailing the research will be presented at the Women in Computer Vision Workshop in Seattle on 14 June.