Projects per year
Abstract
Echo State Networks (ESNs) have shown great promise in the applications of non-linear time series processing because of their powerful computational ability and efficient training strategy. However, the nature of randomization in the structure of the reservoir causes it be poorly understood and leaves room for further improvements for specific problems. A deterministically constructed reservoir model, Cycle Reservoir with Jumps (CRJ), shows superior generalization performance to standard ESN. However, the weights that govern the structure of the reservoir (reservoir weights) in CRJ model are obtained through exhaustive grid search which is very computational intensive. In this paper, we propose to learn the reservoir weights together with the linear readout weights using a hybrid optimization strategy. The reservoir weights are trained through nonlinear optimization techniques while the linear readout weights are obtained through linear algorithms. The experimental results demonstrate that the proposed strategy of training the CRJ network tremendously improves the computational efficiency without jeopardizing the generalization performance, sometimes even with better generalization performance.
Original language | English |
---|---|
Title of host publication | Proceedings of the 2014 International Joint Conference on Neural Networks |
Publisher | Institute of Electrical and Electronics Engineers (IEEE) |
Pages | 77-83 |
Number of pages | 7 |
ISBN (Print) | 9781479914845 |
DOIs | |
Publication status | Published - 3 Sept 2014 |
Event | 2014 International Joint Conference on Neural Networks, IJCNN 2014 - Beijing, China Duration: 6 Jul 2014 → 11 Jul 2014 |
Conference
Conference | 2014 International Joint Conference on Neural Networks, IJCNN 2014 |
---|---|
Country/Territory | China |
City | Beijing |
Period | 6/07/14 → 11/07/14 |
ASJC Scopus subject areas
- Software
- Artificial Intelligence
Fingerprint
Dive into the research topics of 'Learning the deterministically constructed Echo State Networks'. Together they form a unique fingerprint.Projects
- 2 Finished
-
Personalised Medicine through Learning in the Model Space
Tino, P. (Principal Investigator)
Engineering & Physical Science Research Council
1/10/13 → 31/03/17
Project: Research Councils
-
Unified probabilistic modelleing of adaptive spatial temporal structures in the human brain
Tino, P. (Principal Investigator) & Kourtzi, Z. (Co-Investigator)
Biotechnology & Biological Sciences Research Council
1/10/10 → 30/03/14
Project: Research Councils