Initialization of multilayer forecasting artifical neural networks
Neural and Evolutionary Computing
2014-10-24 v1 Methodology
Abstract
In this paper, a new method was developed for initialising artificial neural networks predicting dynamics of time series. Initial weighting coefficients were determined for neurons analogously to the case of a linear prediction filter. Moreover, to improve the accuracy of the initialization method for a multilayer neural network, some variants of decomposition of the transformation matrix corresponding to the linear prediction filter were suggested. The efficiency of the proposed neural network prediction method by forecasting solutions of the Lorentz chaotic system is shown in this paper.
Cite
@article{arxiv.1410.6413,
title = {Initialization of multilayer forecasting artifical neural networks},
author = {Vladimir V. Bochkarev and Yulia S. Maslennikova},
journal= {arXiv preprint arXiv:1410.6413},
year = {2014}
}
Comments
9 pages, 3 figures