Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
9653559 | Neurocomputing | 2005 | 14 Pages |
Abstract
We derive analytical expressions of local codimension-1 bifurcations for a fully connected, additive, discrete-time recurrent neural network (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 oscillator, whose amplitude and frequency can be completely controlled by input parameters.
Related Topics
Physical Sciences and Engineering
Computer Science
Artificial Intelligence
Authors
Robert Haschke, Jochen J. Steil,