Name
Abstract | ||
|---|---|---|
Echo state network contains a randomly connected hidden layer and an adaptable output layer. It can overcome the problems associated with the complex computation and local optima. But there may be ill-posed problem when large reservoir state matrix is used to calculate the output weights by least square estimation. In this study, we use L-1/2 regularization to calculate the output weights to get a sparse solution in order to solve the ill-posed problem and improve the generalized performance. In addition, an operation of iterated prediction is conducted to test the effectiveness of the proposed L1/2ESN for capturing the dynamics of the chaotic time series. Experimental results illustrate that the predictor has been designed properly. It outperforms other modified ESN models in both sparsity and accuracy. |
Year | DOI | Venue |
|---|---|---|
2016 | 10.1007/978-3-319-46675-0_2 | Lecture Notes in Computer Science |
Keywords | Field | DocType |
Echo state networks,L-1/2 norm regularization,Chaotic time series,Prediction | Least squares,Computer science,Matrix (mathematics),Local optimum,Regularization (mathematics),Artificial intelligence,Echo state network,Norm (mathematics),Chaotic,Iterated function,Machine learning | Conference |
Volume | ISSN | Citations |
9949 | 0302-9743 | 0 |
PageRank | References | Authors |
0.34 | 5 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Meiling Xu | 1 | 0 | 0.68 |
| Min Han | 2 | 761 | 68.01 |
| Shunshoku Kanae | 3 | 78 | 11.91 |