Publication View

Input Space Bifurcation Manifolds of RNNs (2009)

Abstract
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 oscillator, whose amplitude and frequency can be completely controlled by input parameters. 1

Publication details
Download http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.144.3452
Source http://www.dice.ucl.ac.be/Proceedings/esann/esannpdf/es2004-84.pdf
Contributors CiteSeerX
Repository CiteSeerX - Scientific Literature Digital Library and Search Engine (United States)
Type text
Language English
Relation 10.1.1.21.8892