A Hilbertian Projection Approach with Dictionary Dividing Strategy: Accelerating Nonlinear Estimation Algorithm with Multiscale Gaussians

Masaaki Takizawa, Masahiro Yukawa

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

A novel dictionary dividing scheme for online non-linear estimation algorithms with multiscale Gaussians is pro-posed to perform a projection in an appropriate reproducing kernel Hilbert space. The proposed dictionary dividing strategy mitigates the in equivalence of the norm of multiscale Gaussians, which leads to degradations of adaptation speed for certain Gaussians. Based on a Hilbertian projection with the dictionary dividing strategy, a fast nonlinear estimation algorithm, which adapts scales and centers of Gaussians as well as its heights, is presented. The numerical example shows that using the Hilber-tian projection with the proposed dictionary dividing scheme ameliorates the adaptation speed of Gaussian heights.

Original languageEnglish
Title of host publication2021 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2021 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2077-2084
Number of pages8
ISBN (Electronic)9789881476890
Publication statusPublished - 2021
Event2021 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2021 - Tokyo, Japan
Duration: 2021 Dec 142021 Dec 17

Publication series

Name2021 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2021 - Proceedings

Conference

Conference2021 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2021
Country/TerritoryJapan
CityTokyo
Period21/12/1421/12/17

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Instrumentation

Fingerprint

Dive into the research topics of 'A Hilbertian Projection Approach with Dictionary Dividing Strategy: Accelerating Nonlinear Estimation Algorithm with Multiscale Gaussians'. Together they form a unique fingerprint.

Cite this