English

Generation of unpredictable time series by a Neural Network

Disordered Systems and Neural Networks 2009-10-31 v2

Abstract

A perceptron that learns the opposite of its own output is used to generate a time series. We analyse properties of the weight vector and the generated sequence, like the cycle length and the probability distribution of generated sequences. A remarkable suppression of the autocorrelation function is explained, and connections to the Bernasconi model are discussed. If a continuous transfer function is used, the system displays chaotic and intermittent behaviour, with the product of the learning rate and amplification as a control parameter.

Keywords

Cite

@article{arxiv.cond-mat/0011302,
  title  = {Generation of unpredictable time series by a Neural Network},
  author = {Richard Metzler and Wolfgang Kinzel and Liat Ein-Dor and Ido Kanter},
  journal= {arXiv preprint arXiv:cond-mat/0011302},
  year   = {2009}
}

Comments

11 pages, 14 figures; slightly expanded and clarified, mistakes corrected; accepted for publication in PRE