Batch Gradient Training Method with Smoothing Regularization for Echo State Networks

Ahmad, Zohaib and Nie, Kaizhe and Qiao, Junfei and Yang, Cuili (2019) Batch Gradient Training Method with Smoothing Regularization for Echo State Networks. In: Machine Learning and Intelligent Communications. 4th International Conference, MLICOM 2019, Nanjing, China, August 24–25, 2019, Proceedings.

[thumbnail of 34652.pdf] PDF
34652.pdf

Download (772kB)

Abstract

The echo state networks (ESNs) have been widely used for time series prediction, due to their excellent learning performance and fast convergence speed. However, the obtained output weight of ESN by pseudoinverse is always ill-posed. In order to solve this problem, the ESN with batch gradient method and smoothing regularization (ESN-BGSL0) is studied. By introducing a smooth regularizer into the traditional error function, some redundant output weights of ESN-BGSL0 are driven to zeros and pruned. Two examples are performed to illustrate the efficiency of the proposed algorithm in terms of estimation accuracy and network compactness.

Item Type: Conference or Workshop Item (UNSPECIFIED)
Date Deposited: 04 Mar 2026 12:35
Last Modified: 20 Nov 2026 11:51
URI: https://eprints.eai.eu/id/eprint/25311

Actions (login required)

View Item
View Item