Time Series Forecasting Using Restricted Boltzmann Machine
In this study, we propose a method for time series prediction using restricted Boltzmann machine (RBM), which is one of stochastic neural networks. The idea comes from Hinton & Salakhutdinov’s multilayer “encoder” network which realized dimensionality reduction of data. A 3-layer deep network of RBMs is constructed and after pre-training RBMs using their energy functions, gradient descent training (error back propagation) is adopted to execute fine-tuning. Additionally, to deal with the problem of neural network structure determination, particle swarm optimization (PSO) is used to find the suitable number of units and parameters. Moreover, a preprocessing, “trend removal” to the original data, was also performed in the forecasting. To compare the proposed predictor with conventional neural network method, i.e., multi-layer perceptron (MLP), CATS benchmark data was used in the prediction experiments.
Keywordstime series forecasting restricted Boltzmann machine multilayer perceptron CATS benchmark
Unable to display preview. Download preview PDF.
- 1.Crone, S., Nikolopoulos, K.: Results of the NN3 neural network forecasting competition. In: The 27 th International Symposium on Forecasting, Program, vol. 129 (2007)Google Scholar
- 5.Hinton, G.E., Sejnowski, T.J.: Learning and Relearning in Boltzmann Machines. In: Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Foundations, vol. 1. MIT Press, Cambridge (1986)Google Scholar
- 7.Kennedy, J., Eberhart, R.C.: Particle Swarm Optimization. In: IEEE International Conference on Neural Networks, pp. 1942–1948 (1995)Google Scholar
- 8.Lendasse, A., Oja, E., Simula, O., Verleysen, M.: Time Series Prediction Competition: The CATS Benchmark. In: International Joint Conference on Neural Networks, pp. 1615–1620 (2004)Google Scholar