Statistical mechanics of lossy compression using multilayer perceptrons
| dc.creator | Mimura, Kazushi | |
| dc.creator | Okada, Masato | |
| dc.date | 2005-08-25 | |
| dc.date | 2006-05-02 | |
| dc.date.accessioned | 2026-07-07T06:41:38Z | |
| dc.date.available | 2026-07-07T06:41:38Z | |
| dc.description | 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. | |
| dc.description | 12 pages, 5 figures | |
| dc.identifier | https://arxiv.org/abs/cond-mat/0508598 | |
| dc.identifier | http://arxiv.org/abs/cond-mat/0508598 | |
| dc.identifier | Phys. Rev. E, 74, 026108 (2006) | |
| dc.identifier | doi:10.1103/PhysRevE.74.026108 | |
| dc.identifier.uri | http://salesiana.dossiersoluciones.com/handle/123456789/101738 | |
| dc.subject | Statistical Mechanics | |
| dc.subject | Disordered Systems and Neural Networks | |
| dc.title | Statistical mechanics of lossy compression using multilayer perceptrons | |
| dc.type | text |