Publication View

Abstract Input Space Bifurcation Manifolds of Recurrent Neural Networks (2008)

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. Key words: bifurcation manifolds, input space, dynamics, recurrent neural network 1

Publication details
Download http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.84.308
Source http://www.techfak.uni-bielefeld.de/ags/ni/publications/media/HaschkeSteil2005-ISB.pdf
Contributors CiteSeerX
Repository CiteSeerX - Scientific Literature Digital Library and Search Engine (United States)
Type text
Language English
Relation 10.1.1.83.1727