Statistical mechanics of lossy compression for non-monotonic multilayer perceptrons

Details Statistical mechanics of lossy compression for non-monotonic multilayer perceptrons Statistical mechanics of lossy compression for non-monotonic multilayer perceptrons

2008-07-25

arxiv.org/abs/0807.4009v1

Phys. Rev. E, 78, 021124 (2008)

Physics

Condensed Matter

Statistical Mechanics

29 pages, 7 figures

Scientific paper

10.1103/PhysRevE.78.021124

A lossy data compression scheme for uniformly biased Boolean messages is investigated via statistical mechanics techniques. We utilize tree-like committee machine (committee tree) and tree-like parity machine (parity tree) whose transfer functions are non-monotonic. The scheme performance at the infinite code length limit is analyzed using the replica method. Both committee and parity treelike networks are shown to saturate the Shannon bound. The AT stability of the Replica Symmetric solution is analyzed, and the tuning of the non-monotonic transfer function is also discussed.

Affiliated with

Also associated with

No associations

Rating

Statistical mechanics of lossy compression for non-monotonic multilayer perceptrons does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Statistical mechanics of lossy compression for non-monotonic multilayer perceptrons, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Statistical mechanics of lossy compression for non-monotonic multilayer perceptrons will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-325405