Reference : Design of a 2-Bit Neural Network Quantizer for Laplacian Source
Scientific journals : Article
Engineering, computing & technology : Computer science
http://hdl.handle.net/10993/47940
Design of a 2-Bit Neural Network Quantizer for Laplacian Source
English
Peric, Zoran mailto [Faculty of Electronic Engineering, University of Nis > Department of Telecommunications]
Savic, Milan mailto [University of Pristina in Kosovska Mitrovica > Faculty of Sciences and Mathematics]
Simic, Nikola mailto [University of Novi Sad > Faculty of Technical Sciences]
Denic, Bojan mailto [Faculty of Electronic Engineering, University of Nis > Department of Telecommunications]
Despotovic, Vladimir mailto [University of Luxembourg > Faculty of Science, Technology and Medicine (FSTM) > Department of Computer Science (DCS) >]
2021
Entropy
Multidisciplinary Digital Publishing Institute (MDPI)
23
8
Methods in Artificial Intelligence and Information Processing)
933
Yes (verified by ORBilu)
1099-4300
Basel
Switzerland
[en] image classification ; Laplacian source ; neural network ; quantization
[en] 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.
Science Fund of the Republic of Serbia
http://hdl.handle.net/10993/47940
10.3390/e23080933
https://www.mdpi.com/1099-4300/23/8/933/htm

File(s) associated to this reference

Fulltext file(s):

FileCommentaryVersionSizeAccess
Open access
entropy-23-00933.pdfPublisher postprint5.73 MBView/Open

Bookmark and Share SFX Query

All documents in ORBilu are protected by a user license.