Reservoir computing and the Sooner-is-Better bottleneck.

Journal: The Behavioral and brain sciences
Published Date:

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."

Authors

  • Stefan L Frank
    Centre for Language Studies,Radboud University Nijmegen,6500 HD Nijmegen,The Netherlands.s.frank@let.ru.nlwww.stefanfrank.info.
  • Hartmut Fitz
    Max Planck Institute for Psycholinguistics, Nijmegen.