DGIST Library Repository

Detail View

  Department of Electrical Engineering and Computer Science Information, Computing, and Intelligence Laboratory 1. Journal Articles
Compression By and For Deep Boltzmann Machines
Citations

WEB OF SCIENCE

Citations

SCOPUS

Metadata Downloads

XML
Excel
Title
Compression By and For Deep Boltzmann Machines
Issued Date
2020-12
Citation
Li, Qing. (2020-12). Compression By and For Deep Boltzmann Machines. IEEE Transactions on Communications, 68(12), 7498–7510. doi: 10.1109/tcomm.2020.3020796
Type
Article
Author Keywords
Image coding ; Rate-distortion ; Noise reduction ; Machine learning ; Training ; Distortion ; Source coding ; Rate distortion ; lossy source coding ; deep Boltzmann machines ; deep auto-encoder ; Blahut-Arimoto algorithm ; denoising
Keywords
CAPACITY ; CODES ; REPRESENTATIONS ; INFORMATION
ISSN
0090-6778
Abstract
We answer two questions in this work: what Deep Boltzmann Machines (DBMs) can do for compression and vise versa. We show that (1) DBMs can be applied to learn the rate distortion approaching posterior as in the Blahut-Arimoto (BA) algorithm, and to construct a lossy source compression scheme based on the Deep AutoEncoder; (2) compression can improve DBMs' training performances via compression-based denoising algorithms. The implementation of the BA algorithm in the form of DBMs is the foundation of the two applications. © 1972-2012 IEEE.
URI
http://hdl.handle.net/20.500.11750/12484
DOI
10.1109/tcomm.2020.3020796
Publisher
Institute of Electrical and Electronics Engineers Inc.
Show Full Item Record

File Downloads

  • There are no files associated with this item.

공유

qrcode
공유하기

Total Views & Downloads