Skip to main navigation Skip to search Skip to main content

An analog network approach to train RBF networks based on sparse recovery

  • Ruibin Feng
  • , Chi-Sing Leung*
  • , A. G. Constantinides
  • *Corresponding author for this work

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review

Abstract

The local competition algorithm (LCA) is an analog neural approach for compressed sensing. It is used to recover a sparse signal from a set of measurements. Unlike some traditional numerical methods that produce many elements with small magnitude, the LCA automatically set those unimportant elements to zero. This paper formulates the training process of radial basis function (RBF) networks as a compressed sensing problem. We then apply the LCA to train RBF networks. The proposed LCA-RBF approach can select important RBF nodes during training. Since the proposed approach can limit the magnitude of the trained weight, it also has certain ability to handle RBF networks with multiplicative weight noise.
Original languageEnglish
Title of host publicationInternational Conference on Digital Signal Processing, DSP
PublisherIEEE
Pages903-908
Volume2014-January
ISBN (Print)9781479946129
DOIs
Publication statusPublished - 2014
Event19th International Conference on Digital Signal Processing (DSP 2014) - Hong Kong, China
Duration: 20 Aug 201423 Aug 2014

Publication series

Name
Volume2014-January

Conference

Conference19th International Conference on Digital Signal Processing (DSP 2014)
PlaceChina
CityHong Kong
Period20/08/1423/08/14

Research Keywords

  • Fault tolerance
  • Local competition algorithm
  • RBF networks

Fingerprint

Dive into the research topics of 'An analog network approach to train RBF networks based on sparse recovery'. Together they form a unique fingerprint.

Cite this