Delayed Recurrent Neural Networks with Global Lipschitz Activation Functions

  • Zhang Yi
  • K. K. Tan
Part of the Network Theory and Applications book series (NETA, volume 13)

Abstract

It is well known that activation functions of RNNs are important characters of RNNs. Usually, activation functions are nonlinear functions, thus they make RNNs be described by nonlinear systems. Since they represent some structural parts of the the nonlinear systems, they crucially decide the dynamical properties of RNNs.

Keywords

Periodic Solution Equilibrium Point Activation Function Convergence Analysis Recurrent Neural Network 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer Science+Business Media Dordrecht 2004

Authors and Affiliations

  • Zhang Yi
    • 1
  • K. K. Tan
    • 2
  1. 1.School of Computer Science and EngineeringUniversity of Electronic Science and Technology of ChinaChengduPeople’s Republic of China
  2. 2.Department of Electrical and Computer EngineeringThe National University of SingaporeSingapore

Personalised recommendations