My way of understanding this is that they're teaching neural networks to dream. This post summarizes work by Gido M. van de Ven et al, Brain-inspired replay for continual learning with artificial neural networks. In sum: "Deep neural networks are the main drivers behind recent AI advances, but progress is held back by this forgetting. They write, 'One solution would be to store previously encountered examples and revisit them when learning something new.'" But this is really slow, so "the team's major insight is in 'recognizing that replay in the brain does not store data.' Rather, 'the brain generates representations of memories at a high, more abstract level with no need to generate detailed memories.'"
Today: 1 Total: 12 [Direct link] [Share]
