Generation of unpredictable time series by a neural network
Abstract
A perceptron that ``learns'' the opposite of its own output is used to generate a time series. We analyze properties of the weight vector and the generated sequence, such as 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 behavior, with the product of the learning rate and amplification as a control parameter.
 Publication:

Physical Review E
 Pub Date:
 May 2001
 DOI:
 10.1103/PhysRevE.63.056126
 arXiv:
 arXiv:condmat/0011302
 Bibcode:
 2001PhRvE..63e6126M
 Keywords:

 84.35.+i;
 05.45.Tp;
 Neural networks;
 Time series analysis;
 Condensed Matter  Disordered Systems and Neural Networks
 EPrint:
 11 pages, 14 figures