Cited 0 time in
Cited 0 time in
Compression By and For Deep Boltzmann Machines
- Compression By and For Deep Boltzmann Machines
- Li, Qing; Chen, Yang; Kim, Yongjune
- DGIST Authors
- Kim, Yongjune
- Issue Date
- IEEE Transactions on Communications, 68(12), 7498-7510
- Article Type
- 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
- CAPACITY; CODES; REPRESENTATIONS; INFORMATION
- 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.
- Institute of Electrical and Electronics Engineers Inc.
- Related Researcher
Information, Computing, and Intelligence Laboratory
machine learning, artificial intelligence, information theory, coding theory, storage, computing
There are no files associated with this item.
- Department of Information and Communication EngineeringInformation, Computing, and Intelligence Laboratory1. Journal Articles
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.