- Some types of artificial intelligence could start to hallucinate if they don’t get enough rest, just as humans do.
- This sort of instability is not a characteristic of all AI networks. The issue only arises when training biologically realistic processors, or when trying to understand biology itself.
- Our realization came about as we worked to develop neural networks that closely approximate how humans and other biological systems learn to see. We were investigating the way that these simulated networks respond to unsupervised dictionary training.
- The vast majority of researchers on machine learning, deep learning and AI never encounter this instability because, in the very artificial systems they study, they have the luxury of performing mathematical operations that have no equivalent in living neurons.
- The results suggest that in both artificial and natural intelligence systems slow-wave sleep may act to ensure that neurons maintain their stability and do not hallucinate.
- When we exposed the networks to states that are analogous to the waves that living brains experience during sleep, stability was restored. It was as though we were giving the neural networks the equivalent of a good, long nap.
- Sleeplike states in neural networks are very different from the mode your PC enters after some set period of inactivity. A conventional computer that has gone to “sleep” is effectively in suspended animation, with all computational activity frozen in time. And the age-old advice from the IT department to try “turning your computer off and then on again” when a PC gets glitchy is tantamount to exposing your machine to a brief period of brain death.
- We expect that sophisticated AI systems will help us to more fully understand sleep and other characteristics in biological systems. The napping toaster of the future may provide novel insights into the workings of our brains—in addition to a warm and crispy breakfast food.
- We are just starting to investigate an additional benefit of artificial sleep in our simulations. Often, a few neurons in a simulated network fail to function at all when a simulation is started. We have found that applying artificial sleep states seems to reset idle neurons to ensure they become functioning components in the network.
Category 2: The Big Picture of The Digital Age
[genioux fact extracted from Scientific American]
Authors of the genioux fact