2000/07/05 by Avner Priel, A. Priel, Ido Kanter +1 · 17 citations
Computer Science · Mathematics · Physics and Astronomy · #Applied mathematics #Artificial intelligence #Artificial neural network #Attractor #Biology #CHAOS (operating system) #Chaos control and synchronization #Computer science #Control (management) #Control theory (sociology) #Dimension (graph theory) #Function (biology) #Mathematical analysis #Mathematics #Monotonic function #Multilayer perceptron #Neural Networks and Applications #Nonlinear Dynamics and Pattern Formation #Perceptron #Pure mathematics #Series (stratigraphy) #cond-mat.dis-nn #nlin.CD
paper · pdf · doi:10.1209/epl/i2000-00521-4
published in Europhysics Letters (EPL) 51(2), 230-236 (Institute of Physics) · 7 pages, 5 figures (reduced quality), accepted for publication in EuroPhysics Letters
arxiv created 2000/07/05 · openalex publication_date 2000/07/15 · arxiv updated 2009/11/30 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
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. The 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.