Design of a 2-bit neural network quantizer for laplacian source

Zoran Perić, Milan Savić, Nikola Simić*, Bojan Denić, Vladimir Despotović

*Corresponding author for this work

Research output: Contribution to journalArticleResearchpeer-review

8 Citations (Scopus)

Abstract

Achieving real-time inference is one of the major issues in contemporary neural network applications, as complex algorithms are frequently being deployed to mobile devices that have constrained storage and computing power. Moving from a full-precision neural network model to a lower representation by applying quantization techniques is a popular approach to facilitate this issue. Here, we analyze in detail and design a 2-bit uniform quantization model for Laplacian source due to its significance in terms of implementation simplicity, which further leads to a shorter processing time and faster inference. The results show that it is possible to achieve high classification accuracy (more than 96% in the case of MLP and more than 98% in the case of CNN) by implementing the proposed model, which is competitive to the performance of the other quantization solutions with almost optimal precision.

Original languageEnglish
Article number933
JournalEntropy
Volume23
Issue number8
DOIs
Publication statusPublished - Aug 2021
Externally publishedYes

Keywords

  • Image classification
  • Laplacian source
  • Neural network
  • Quantization

Fingerprint

Dive into the research topics of 'Design of a 2-bit neural network quantizer for laplacian source'. Together they form a unique fingerprint.

Cite this