2026-03-09T09:29:50Z https://hiroshima-cu.repo.nii.ac.jp/oai

oai:hiroshima-cu.repo.nii.ac.jp:00001318 2023-07-25T10:47:26Z 1:214

Statistical mechanics of lossy compression using multilayer perceptrons MIMURA, Kazushi ミムラ, カズシ OKADA, Masato オカダ, マサト 三村, 和史 岡田, 真人 © 2008 The American Physical Society application/pdf Statistical mechanics is applied to lossy compression using multilayer perceptrons for unbiased Boolean messages. We utilize a treelike committee machine committee tree and treelike parity machine parity tree whose transfer functions are monotonic. For compression using a 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→ . 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. American Physical Society 2006-08 eng journal article VoR https://hiroshima-cu.repo.nii.ac.jp/records/1318 AA11558033 1539-3755 Physical Review E - Statistical, Nonlinear, and Soft Matter Physics 74 2 026108-1 026108-11 https://hiroshima-cu.repo.nii.ac.jp/record/1318/files/Mimura.K_PRE_74_026108_2006.pdf application/pdf 154.0 kB 2023-02-28