Title :
Forecast chaotic time series data by DBNs
Author :
Kuremoto, Takashi ; Obayashi, Masanao ; Kobayashi, Kaoru ; Hirata, Takaomi ; Mabu, Shingo
Author_Institution :
Grad. Sch. of Sci. & Eng., Yamaguchi Univ., Ube, Japan
Abstract :
Deep belief nets (DBNs) with multiple artificial neural networks (ANNs) have attracted many researchers recently. In this paper, we propose to compose restricted Boltzmann machine (RBM) and multi-layer perceptron (MLP) as a DBN to predict chaotic time series data, such as the Lorenz chaos and the Henon map. Experiment results showed that in the sense of prediction precision, the novel DBN performed better than the conventional DBN with RBMs.
Keywords :
Boltzmann machines; Henon mapping; chaos; data analysis; multilayer perceptrons; time series; DBN; Henon map; Lorenz chaos; MLP; RBM; chaotic time series data forecasting; chaotic time series data prediction; deep belief networks; multilayer perceptron; restricted Boltzmann machine; Artificial neural networks; Chaos; Educational institutions; Feature extraction; Forecasting; Predictive models; Time series analysis; Deep Belief Net; Deep learning; chaos; forecasting;
Conference_Titel :
Image and Signal Processing (CISP), 2014 7th International Congress on
Conference_Location :
Dalian
DOI :
10.1109/CISP.2014.7003950
