Physics – Condensed Matter
Scientific paper
1997-03-03
Physics
Condensed Matter
LaTeX 20 pages using IOP LaTeX preprint style file, 14 figures
Scientific paper
10.1088/0305-4470/30/11/012
We study the generalization ability of a simple perceptron which learns unlearnable rules. The rules are presented by a teacher perceptron with a non-monotonic transfer function. The student is trained in the on-line mode. The asymptotic behaviour of the generalization error is estimated under various conditions. Several learning strategies are proposed and improved to obtain the theoretical lower bound of the generalization error.
Inoue Jun'ichi
Kabashima Yoshiyuki
Nishimori Hidetoshi
No associations
LandOfFree
On-line learning of non-monotonic rules by simple perceptron 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 On-line learning of non-monotonic rules by simple perceptron, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and On-line learning of non-monotonic rules by simple perceptron will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-47172