Name
Abstract | ||
|---|---|---|
Echo state network is a novel recurrent neural network, with a fixed reservoir structure and an adaptable linear readout layer, facilitating the application of RNNs. Often the network works beautifully. But sometimes it works poorly because of ill-posed problem. To solve it, we introduce a new approach towards ESNs, termed FSDESN, herein. It combines the merits of ESNs and fast subspace decomposition algorithm to provide a more precise alternative to conventional ESNs. The basic idea is to extract the subspace of the redundant large-scale reservoir state matrix by Krylov subspace decomposition algorithm, subsequently, calculate the readout weights using the subspace to replace original reservoir matrix. Hence, it can eliminate approximate collinear components and overcome the ill-posed problems so as to improve generalization performance. We exhibit the merits of our model in two multivariate benchmark datasets. Experimental results substantiate the effectiveness and characteristics of FSDESN. |
Year | DOI | Venue |
|---|---|---|
2012 | 10.1007/978-3-642-34500-5_80 | ICONIP (5) |
Keywords | Field | DocType |
multivariate time series prediction,redundant large-scale reservoir state,subspace decomposition algorithm,subspace echo state network,echo state network,original reservoir matrix,conventional esns,ill-posed problem,fixed reservoir structure,readout weight,adaptable linear readout layer,novel recurrent neural network | Krylov subspace,Time series,Subspace topology,Pattern recognition,Computer science,Matrix (mathematics),Multivariate statistics,Recurrent neural network,Reservoir computing,Artificial intelligence,Echo state network,Machine learning | Conference |
Volume | ISSN | Citations |
7667 | 0302-9743 | 0 |
PageRank | References | Authors |
0.34 | 5 | 2 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Min Han | 1 | 761 | 68.01 |
| Meiling Xu | 2 | 0 | 0.68 |