Vector quantization using k-means clustering neural network

Research output: Contribution to journalArticlepeer-review

4 Citations (Scopus)

Abstract

Vector Quantization (VQ) is a clustering problem in the fields of signal processing, source coding, information theory etc. Taking advantage of recent advances in the field of deep neural networks, this paper investigates the performance between VQ clustering problems and deep neural networks. A k-means-based deep network architecture for VQ is presented to solve clustering problems. By applying the deep learning implementation of convergence optimization, a clustering neural network (algorithm) for the purpose of VQ is proposed. In practice, the proposed network quantifies the vectors over a set of stacked neural layers, overcoming the exponential complexity problem of VQ methods by trainable parameters. Experiments show that the work can improve the results without human intervention, and outperforms traditional clustering methods modified for VQ.

Original languageEnglish
Article numbere12758
JournalElectronics Letters
Volume59
Issue number7
DOIs
Publication statusPublished - Apr 2023

Keywords

  • neural nets
  • pattern clustering

Fingerprint

Dive into the research topics of 'Vector quantization using k-means clustering neural network'. Together they form a unique fingerprint.

Cite this