Robust chaos generation by a perceptron

Abstract

The properties of time series generated by a perceptron with monotonic and non-monotonic transfer function, where the next input vector is determined from past output values, are examined. Analysis of the parameter space reveals the following main finding: a perceptron with a monotonic function can produce fragile chaos only whereas a non-monotonic function can generate robust chaos as well. For non-monotonic functions, the dimension of the attractor can be controlled monotonically by tuning a natural parameter in the model.

7 pages, 5 figures (reduced quality), accepted for publication in EuroPhysics Letters

References in corpus (2)

• Long-term properties of time series generated by a perceptron with various transfer functions
• Chaos in neural networks with a nonmonotonic transfer function

Cited by in corpus (4)

• Learning and predicting time series by neural networks
• The gluon condensation at high energy hadron collisions
• Robust chaos with variable Lyapunov exponent in smooth one-dimensional maps
• Amplitude death in coupled robust-chaos oscillators