On the conditions for the existence of Perfect Learning and power law in learning from stochastic examples by Ising perceptrons

Details On the conditions for the existence of Perfect Learning and power law in learning from stochastic examples by Ising perceptrons On the conditions for the existence of Perfect Learning and power law in learning from stochastic examples by Ising perceptrons

2001-06-29

arxiv.org/abs/cond-mat/0106654v1

Physics

Condensed Matter

Disordered Systems and Neural Networks

28 pages, 43 figures. Submitted to J. Phys. A

Scientific paper

10.1143/JPSJ.71.1882

In a previous letter, we studied learning from stochastic examples by perceptrons with Ising weights in the framework of statistical mechanics. Under the one-step replica symmetry breaking ansatz, the behaviours of learning curves were classified according to some local property of the rules by which examples were drawn. Further, the conditions for the existence of the Perfect Learning together with other behaviors of the learning curves were given. In this paper, we give the detailed derivation about these results and further argument about the Perfect Learning together with extensive numerical calculations.

Affiliated with

Also associated with

No associations

Rating

On the conditions for the existence of Perfect Learning and power law in learning from stochastic examples by Ising 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 On the conditions for the existence of Perfect Learning and power law in learning from stochastic examples by Ising perceptrons, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and On the conditions for the existence of Perfect Learning and power law in learning from stochastic examples by Ising perceptrons will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-646258