A dictionary updating scheme incorporating words elimination into Quantized Kernel Least-Mean-Squares for changing environments

Lei Sun, Badong Chen, Shengyu Nan, Zhiping Lin, Kar Ann Toh

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Citations (Scopus)

Abstract

Learning under time-varying environment is a challenging task since one has to deal with the ever changing distribution of data. A common and yet effective solution is to learn the data online and keep up with any ongoing changes. The Quantized Kernel Least-Squares (QKLMS) is an effective tool for online dictionary learning where the network size is capped by the quantization dictionary size. However, due to the lack of a mechanism to eliminate outdated words, learning can become irrelevant over time. In this paper, a mechanism to remove irrelevant words in the dictionary is proposed for QKLMS. Our experimental results based on chaotic time sequence prediction validate the capability of the developed method for time-varying data adaptation.

Original languageEnglish
Title of host publication2015 IEEE International Conference on Digital Signal Processing, DSP 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages911-915
Number of pages5
ISBN (Electronic)9781479980581, 9781479980581
DOIs
Publication statusPublished - 9 Sept 2015
EventIEEE International Conference on Digital Signal Processing, DSP 2015 - Singapore, Singapore
Duration: 21 Jul 201524 Jul 2015

Publication series

NameInternational Conference on Digital Signal Processing, DSP
Volume2015-September

Conference

ConferenceIEEE International Conference on Digital Signal Processing, DSP 2015
Country/TerritorySingapore
CitySingapore
Period21/07/1524/07/15

Keywords

  • Changing environment learning
  • Kernel learning machine
  • Online learning
  • Vector quantization

Fingerprint

Dive into the research topics of 'A dictionary updating scheme incorporating words elimination into Quantized Kernel Least-Mean-Squares for changing environments'. Together they form a unique fingerprint.

Cite this