Journal
IEEE ACCESS
Volume 6, Issue -, Pages 10720-10732Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/ACCESS.2018.2810190
Keywords
Echo state network; adaptive Levenberg-Marquardt algorithm; trust region technique; weight initialization; chaotic time series prediction
Categories
Funding
- National Natural Science Foundation of China [61533002, 61603012]
- Beijing Municipal Education Commission Foundation [KM20170005025]
- Beijing Post-Doctoral Research Foundation of China [2017ZZ-028]
- China Post-Doctoral Science Foundation
Ask authors/readers for more resources
Echo state networks (ESNs) have wide applications in chaotic time series prediction. In the ESN, if the smallest singular value of the reservoir state matrix is infinitesimal, the ill-posed problem might occur during the training process. To overcome this problem, an adaptive Levenberg Marquardt (LM) algorithm-based echo state network (ALM-ESN) is developed. In the developed ALM-ESN, a new adaptive damping term is introduced into the LM algorithm. The adaptive factor is amended by the trust region technique, furthermore, convergence analysis, and stability analysis are performed. Moreover, to make the inputs fall within the active region of the activation function and improve the learning speed, a weight initialization method using linear algebra is deployed to determine the appropriate input weights and reservoir weights. Simulations demonstrate that the ALM-ESN can overcome the ill-posed problem. Furthermore, it exhibits better performance and robustness for chaotic time series prediction than some other existing methods.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available