Name
Abstract | ||
|---|---|---|
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. |
Year | DOI | Venue |
|---|---|---|
2012 | 10.1007/978-3-642-31837-5_3 | Communications in Computer and Information Science |
Keywords | Field | DocType |
time series forecasting,restricted Boltzmann machine,multilayer perceptron,CATS benchmark | Particle swarm optimization,Restricted Boltzmann machine,Gradient descent,Pattern recognition,Computer science,Stochastic neural network,Multilayer perceptron,Artificial intelligence,Backpropagation,Artificial neural network,Perceptron,Machine learning | Conference |
Volume | ISSN | Citations |
304 | 1865-0929 | 9 |
PageRank | References | Authors |
0.69 | 3 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Takashi Kuremoto | 1 | 196 | 27.73 |
| Shinsuke Kimura | 2 | 90 | 3.40 |
| Kunikazu Kobayashi | 3 | 173 | 21.96 |
| Masanao Obayashi | 4 | 198 | 26.10 |