Physics – Condensed Matter – Disordered Systems and Neural Networks
Scientific paper
1999-09-16
Physics
Condensed Matter
Disordered Systems and Neural Networks
13 pages, 1 figure
Scientific paper
10.1088/0305-4470/33/9/301
Upper and lower bounds for the typical storage capacity of a constructive algorithm, the Tilinglike Learning Algorithm for the Parity Machine [M. Biehl and M. Opper, Phys. Rev. A {\bf 44} 6888 (1991)], are determined in the asymptotic limit of large training set sizes. The properties of a perceptron with threshold, learning a training set of patterns having a biased distribution of targets, needed as an intermediate step in the capacity calculation, are determined analytically. The lower bound for the capacity, determined with a cavity method, is proportional to the number of hidden units. The upper bound, obtained with the hypothesis of replica symmetry, is close to the one predicted by Mitchinson and Durbin [Biol. Cyber. {\bf 60} 345 (1989)].
Buhot Arnaud
Gordon Mirta B.
No associations
LandOfFree
Storage capacity of a constructive learning algorithm 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 Storage capacity of a constructive learning algorithm, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Storage capacity of a constructive learning algorithm will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-712406