A. Priel, I. Kanter
Published 2000-07-05Version 1
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.
Comments: 7 pages, 5 figures (reduced quality), accepted for publication in EuroPhysics Letters
Journal: EuroPhysics Letters 51 (2), p. 230 (2000)
Generalization ability of a perceptron with non-monotonic transfer function
Generalizing with perceptrons in case of structured phase- and pattern-spaces
Multifractality and percolation in the coupling space of perceptrons
