arXiv · cond-mat/0508598
Statistical mechanics of lossy compression using multilayer perceptrons
Abstract
Statistical mechanics is applied to lossy compression using multilayer perceptrons for unbiased Boolean messages. We utilize a tree-like committee machine (committee tree) and tree-like parity machine (parity tree) whose transfer functions are monotonic. For compression using committee tree, a lower bound of achievable distortion becomes small as the number of hidden units K increases. However, it cannot reach the Shannon bound even where K -> infty. For a compression using a parity tree with K >= 2 hidden units, the rate distortion function, which is known as the theoretical limit for compression, is derived where the code length becomes infinity.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Kazushi Mimura, Masato Okada. 2006-05-02. Statistical mechanics of lossy compression using multilayer perceptrons. https://doi.org/10.1103/physreve.74.026108. https://searcharxiv.com/abs/cond-mat/0508598
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.