自动化学报2011，Vol.37Issue(12)：1536-1540,5.DOI:10.3724/SP.J.1004.2011.01536
一种有效的储备池在线稀疏学习算法
An Effective Online Sparse Learning Algorithm for Echo State Networks
摘要
Abstract
In order to overcome the lack of effective online learning method for echo state networks and to solve the ill-posed problem of reservoir, an effective online sparse learning algorithm is proposed for echo state networks in this paper. An Li regularization constraint is added to the objective function of reservoir, and a truncated gradient algorithm is used to approximately solve the problem online. The proposed method can adjust the output weights of reservoir online, control the spar-sity of the output weights, and ensure the generalization performance. Theoretical analysis and simulation results demonstrate the effectiveness of the algorithm.关键词
递归网络/回声状态网络/稀疏/在线/优化Key words
Recurrent neural networks, echo state networks (ESNs)/sparse/online/optimization引用本文复制引用
韩敏,王新迎..一种有效的储备池在线稀疏学习算法[J].自动化学报,2011,37(12):1536-1540,5.基金项目
国家自然科学基金(61074096)资助 （61074096）
