Back

Title
  • en An Online Self-Constructive Normalized Gaussian Network with Localized Forgetting
Creator
Accessrights open access
Rights
  • en copyright©2017 IEICE
Subject
  • Other en Normalized Gaussian Networks
  • Other en dynamic model selection
  • Other en online learning
  • Other en chaotic time series forecasting
  • NDC 007
Description
  • Abstract en In this paper, we introduce a self-constructive Normalized Gaussian Network (NGnet) for online learning tasks. In online tasks, data samples are received sequentially, and domain knowledge is often limited. Then, we need to employ learning methods to the NGnet that possess robust performance and dynamically select an accurate model size. We revise a previously proposed localized forgetting approach for the NGnet and adapt some unit manipulation mechanisms to it for dynamic model selection. The mechanisms are improved for more robustness in negative interference prone environments, and a new merge manipulation is considered to deal with model redundancies. The effectiveness of the proposed method is compared with the previous localized forgetting approach and an established learning method for the NGnet. Several experiments are conducted for a function approximation and chaotic time series forecasting task. The proposed approach possesses robust and favorable performance in different learning situations over all testbeds.
Publisher ja 電子情報通信学会 en The Institute of Electronics, Information and Communication Engineers / IEICE
Date
    Issued2017-03
Language
  • eng
Resource Type journal article
Version Type VoR
Identifier HDL http://hdl.handle.net/2115/65552
Relation
  • URI http://search.ieice.org/
  • isIdenticalTo DOI https://doi.org/10.1587/transfun.E100.A.865
Journal
    • PISSN 1745-1337
      • en IEICE transactions on fundamentals of electronics communications and computer sciences
      • Volume NumberE100 Issue Number3 Page Start865 Page End876
File
Oaidate 2023-07-26