一种基于池计算的宽度学习系统
作者:
作者单位:

华东交通大学,电气与自动化工程学院

作者简介:

通讯作者:

中图分类号:

TP183

基金项目:

国家自然科学基金项目(61663012, 61673172, 61733005)


A Board Learning System based on Reservoir Computing
Author:
Affiliation:

East China Jiaotong University

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:

    宽度学习系统BLS是一种基于RVFLN的高效增量学习系统, 具有快速且精度高的特点. 为了实现BLS对时间序列的精确预测, 结合回声状态网络ESN的储备池结构, 提出一种基于池计算的宽度学习系统RCBLS. 该系统通过在强化层引入简单环型储备池连接, 以并行的储备池代替原系统中的前馈连接, 使RCBLS具有一定的回声状态特性且方便设计. 同时, 应用增量学习保证了系统的实时性能. 基于MSO时间序列预测问题, 针对不同规模数据样本分别研究了不同储备池结构RCBLS 的性能. 结果表明: 多储备池结构的RCBLS大大提高了模型的泛化能力和稳定性.

    Abstract:

    The Broad Learning System (BLS), which has characteristics of fast and accuracy, is an efficient incremental learning system based on RVFLN. In order to realize the precise prediction of time-series, a Broad Learning System based on Reservoir Computing (RCBLS) is proposed ,which combined of the Reservoir structure of Echo State Network (ESN). A simple circle reservoir connection was introduced in the RCBLS’s enhancement layer to replace the feedforward connection of BLS, which makes RCBLS have certain Echo State characteristics and convenient for design. At the same time, incremental learning is applied to ensure RCBLS’s real-time performance. Based on the MSO time series prediction problems, the performance of RCBLS with different reservoir structures under different scales of data sample are studied respectively. The results show that RCBLS with multi-reservoir structure improved the generalization performance and the stability greatly.

    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:2019-12-10
  • 最后修改日期:2021-03-22
  • 录用日期:2020-03-06
  • 在线发布日期:
  • 出版日期: