Time series generation by multilayer networks
Authors:
- 1 June 1998
- journal article
- research article
- Published by American Physical Society (APS) in Physical Review E
- Vol. 57 (6) , 6564-6572
Abstract
The properties of time series, generated by continuous valued multilayer networks consisting of one or two hidden layers, are studied analytically. The time series is generated by using past output values to determine the next input vector. The main results for the generic asymptotic behavior are (a) The attractor dimension is only a function of the number of hidden units in the first hidden layer; (b) the analytical solution for the time series generated by the networks mirrors the structure of the network itself.Keywords
This publication has 6 references indexed in Scilit:
- Training a perceptron by a bit sequence: storage capacityJournal of Physics A: General Physics, 1996
- Analytical Study of Time Series Generation by Feed-Forward NetworksPhysical Review Letters, 1995
- Generation and Prediction of Time Series by a Neural NetworkPhysical Review Letters, 1995
- The statistical mechanics of learning a ruleReviews of Modern Physics, 1993
- EmbedologyJournal of Statistical Physics, 1991
- Handbook of Mathematical FunctionsAmerican Journal of Physics, 1966