Version 1
: Received: 20 October 2018 / Approved: 22 October 2018 / Online: 22 October 2018 (12:24:43 CEST)
How to cite:
Chen, Q.; Pan, G.; Yu, M.; Wang, J. Unsupervised Feature Learning in Time Series Prediction Using Continuous Deep Belief Network. Preprints2018, 2018100494. https://doi.org/10.20944/preprints201810.0494.v1
Chen, Q.; Pan, G.; Yu, M.; Wang, J. Unsupervised Feature Learning in Time Series Prediction Using Continuous Deep Belief Network. Preprints 2018, 2018100494. https://doi.org/10.20944/preprints201810.0494.v1
Chen, Q.; Pan, G.; Yu, M.; Wang, J. Unsupervised Feature Learning in Time Series Prediction Using Continuous Deep Belief Network. Preprints2018, 2018100494. https://doi.org/10.20944/preprints201810.0494.v1
APA Style
Chen, Q., Pan, G., Yu, M., & Wang, J. (2018). Unsupervised Feature Learning in Time Series Prediction Using Continuous Deep Belief Network. Preprints. https://doi.org/10.20944/preprints201810.0494.v1
Chicago/Turabian Style
Chen, Q., Ming Yu and Jiuhe Wang. 2018 "Unsupervised Feature Learning in Time Series Prediction Using Continuous Deep Belief Network" Preprints. https://doi.org/10.20944/preprints201810.0494.v1
Abstract
A continuous Deep Belief Network (cDBN) with two hidden layers is proposed in this paper, focusing on the problem of weak feature learning ability when dealing with continuous data. In cDBN, the input data is trained in an unsupervised way by using continuous version of transfer functions, the contrastive divergence is designed in hidden layer training process to raise convergence speed, an improved dropout strategy is then implemented in unsupervised training to realize features learning by de-cooperating between the units, and then the network is fine-tuned using back propagation algorithm. Besides, hyper-parameters are analysed through stability analysis to assure the network can find the optimal. Finally, the experiments on Lorenz chaos series, CATS benchmark and other real world like CO2 and waste water parameters forecasting show that cDBN has the advantage of higher accuracy, simpler structure and faster convergence speed than other methods.
Keywords
unsupervised training; features learning; deep learning; time series forecasting
Subject
Computer Science and Mathematics, Artificial Intelligence and Machine Learning
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.