Average Competitive Learning Vector Quantization

Abstract : We propose a new algorithm for vector quantization:Average Competitive Learning Vector Quantization(ACLVQ). It is a rather simple modi cation of the classical Competitive Learning Vector Quantization(CLVQ). This new formulation gives us similar results for the quantization error to those obtained by the CLVQ and reduce considerably the computation time to achieve the optimal quantizer. We establish the convergence of the method via the Kushner-Clark approach, and compare the two algorithms via the central limit Theorem. A simulation study is carried out showing the good performance of our proposal.
Document type :
Preprints, Working Papers, ...
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-00685960
Contributor : Jean-Claude Fort <>
Submitted on : Friday, April 6, 2012 - 2:44:17 PM
Last modification on : Wednesday, November 6, 2019 - 3:36:06 PM
Long-term archiving on: Wednesday, December 14, 2016 - 8:44:49 PM

File

ACLVQ_4.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00685960, version 1

Collections

Citation

Luis Armando Salomon, Jean-Claude Fort, Li-Vang Lozada Chang. Average Competitive Learning Vector Quantization. 2012. ⟨hal-00685960⟩

Share

Metrics

Record views

235

Files downloads

390