基于增量式学习的正则化回声状态网络
作者:
作者单位:

1.北京信息科技大学自动化学院;2.北京工业大学信息学部

作者简介:

通讯作者:

中图分类号:

TP183

基金项目:

国家重点研发计划项目,国家自然科学基金项目(面上项目,重点项目,重大项目)


Design of Incremental Regularized Echo State Network
Author:
Affiliation:

1.Beijing information Science and Technology University;2.Beijing University of Technology

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    针对回声状态网络(Echo state network, ESN)的结构设计问题,提出增量式正则化回声状态网络(Incremental regularized echo state network, IRESN)。该网络由相互独立的子储备池模块构成,首先,子储备池根据奇异值分解方法生成,且可以保证每个子储备池权值矩阵的奇异值都小于1。其次,利用问题复杂度或者残差,将网络中逐一添加子储备池,直至满足预设的终止条件,在生成IRESN的过程中,回声状态特性能够得以保证,并不需要缩放储备池权值矩阵。同时,为了解决不适定问题,在网络增量式学习过程中,利用正则化方法训练输出权值,并利用留一交叉验证方法选择正则化参数。仿真结果表明,与其他ESNs相比较,所得网络具有紧凑的结构和较高的预测精度。

    Abstract:

    Aiming at the structure design of echo state network (ESN), an incremental regularized echo state network (IRESN) is proposed in this paper. The reservoir of IRESN is composed of independent sub-reservoir modular networks. First, the sub-reservoirs are obtained using the singular value decomposition method, and the singular values of the weight matrix of each sub-reservoir can be guaranteed to be less than one. Second, depending on the problem complexity or residual error, the sub-reservoirs are added to the network one after another until the preset termination conditions are met. In the process of generating IRESN, the echo state property can be guaranteed without scaling the reservoir weight matrix. In order to tackle the ill-posed problem, in the process of incremental learning, the output weights are trained by regularization method, the leave-one-out cross-validation method is used to select the regularization parameter. The simulation results show that the IRESN has compact structure and high prediction accuracy compared with other ESNs.

    参考文献
    相似文献
    引证文献
引用本文
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2020-09-19
  • 最后修改日期:2021-10-21
  • 录用日期:2020-12-25
  • 在线发布日期: 2021-02-04
  • 出版日期: