AI is still a long way from matching human intelligence, but one way it might already mirror mere mortals is in its need for sleep. Researchers from Los Alamos National Laboratory made the discovery while developing neural networks that learn in a similar way as a human brain. They found that the artificial brains became unstable after continuous periods of unsupervised dictionary training. This technique involves classifying objects without comparing them to existing examples, which I’d find pretty exhausting too. They tried to overcome the problem by exposing the networks to noise signals that created an artificial version of sleep. When they used… This story continues at The Next Web…
Leave a Reply