Physics – Condensed Matter – Disordered Systems and Neural Networks
Scientific paper
1999-06-24
J. Phys. A: Math. Gen. 32, L555-L560 (1999)
Physics
Condensed Matter
Disordered Systems and Neural Networks
6 pages, 1 figure; small changes
Scientific paper
10.1088/0305-4470/32/3/010
We study a simple model of unsupervised learning where the single symmetry breaking vector has binary components $\pm 1$. We calculate exactly the Bayes-optimal performance of an estimator which is required to lie in the same discrete space. We also show that, except for very special cases, such an estimator cannot be obtained by minimization of a class of variationally optimal potentials.
Copelli Mauro
den Broeck Chris Van
Opper Manfred
No associations
LandOfFree
Bayes-optimal performance in a discrete space 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 Bayes-optimal performance in a discrete space, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Bayes-optimal performance in a discrete space will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-429989