What happened
Researchers discovered that recurrent neural networks can learn in real time using only 6% of the gradient calculations normally required, without losing accuracy. This means AI systems that need to adapt instantly to changing conditions can do so much faster and cheaper, especially as they get larger.
Why it matters
Online learning — where a system adapts to new information in real time rather than waiting for a batch of training data — has been computationally expensive enough to be impractical; this makes it feasible at scale by showing the redundancy in gradient computation was far larger than anyone assumed.