Input Space Bifurcation Manifolds of RNNs

Abstract

We derive analytical expressions of local codim-1-bifurcations for a fully connected, additive, discrete-time RNN, where we regard the external inputs as bifurcation parameters. The complexity of the bifurcation diagrams obtained increases exponentially with the number of neurons. We show that a three-neuron cascaded network can serve as a universal… (More)

4 Figures and Tables

Topics

  • Presentations referencing similar topics