Design and analysis of binary scalar quantizer of laplacian source with applications

Zoran Peric, Bojan Denic*, Milan Savic, Vladimir Despotovic

*Corresponding author for this work

Research output: Contribution to journalArticleResearchpeer-review

13 Citations (Scopus)

Abstract

A compression method based on non-uniform binary scalar quantization, designed for the memoryless Laplacian source with zero-mean and unit variance, is analyzed in this paper. Two quantizer design approaches are presented that investigate the effect of clipping with the aim of reducing the quantization noise, where the minimal mean-squared error distortion is used to determine the optimal clipping factor. A detailed comparison of both models is provided, and the performance evaluation in a wide dynamic range of input data variances is also performed. The observed binary scalar quantization models are applied in standard signal processing tasks, such as speech and image quantization, but also to quantization of neural network parameters. The motivation behind the binary quantization of neural network weights is the model compression by a factor of 32, which is crucial for implementation in mobile or embedded devices with limited memory and processing power. The experimental results follow well the theoretical models, confirming their applicability in real-world applications.

Original languageEnglish
Article number501
Pages (from-to)1-18
Number of pages18
JournalInformation (Switzerland)
Volume11
Issue number11
DOIs
Publication statusPublished - Nov 2020
Externally publishedYes

Keywords

  • Clipping factor
  • Delta modulation
  • Laplacian distribution
  • Neural network
  • Pulse code modulation
  • Quantization
  • Signal to noise ratio

Fingerprint

Dive into the research topics of 'Design and analysis of binary scalar quantizer of laplacian source with applications'. Together they form a unique fingerprint.

Cite this