Reservoir computing and the Sooner-is-Better bottleneck.
Journal:
The Behavioral and brain sciences
Published Date:
Jan 1, 2016
Abstract
Prior language input is not lost but integrated with the current input. This principle is demonstrated by "reservoir computing": Untrained recurrent neural networks project input sequences onto a random point in high-dimensional state space. Earlier inputs can be retrieved from this projection, albeit less reliably so as more input is received. The bottleneck is therefore not "Now-or-Never" but "Sooner-is-Better."