Rigorous Bounds to Retarded Learning

Details Rigorous Bounds to Retarded Learning Rigorous Bounds to Retarded Learning

2002-01-15

arxiv.org/abs/cond-mat/0201256v1

Physics

Condensed Matter

Disordered Systems and Neural Networks

1 page, 1 figure. Comment accepted for publication in Physical Review Letters

Scientific paper

10.1103/PhysRevLett.88.099801

We show that the lower bound to the critical fraction of data needed to infer (learn) the orientation of the anisotropy axis of a probability distribution, determined by Herschkowitz and Opper [Phys.Rev.Lett. 86, 2174 (2001)], is not always valid. If there is some structure in the data along the anisotropy axis, their analysis is incorrect, and learning is possible with much less data points.

Affiliated with

Also associated with

No associations

Rating

Rigorous Bounds to Retarded Learning 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 Rigorous Bounds to Retarded Learning, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Rigorous Bounds to Retarded Learning will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-553937