Monthly
288 pp. per issue
6 x 9, illustrated
ISSN
0899-7667
E-ISSN
1530-888X
2014 Impact factor:
2.21

Neural Computation

January 1, 1997, Vol. 9, No. 1, Pages 99-122
(doi: 10.1162/neco.1997.9.1.99)
© 1997 Massachusetts Institute of Technology
Playing Billiards in Version Space
Article PDF (619.87 KB)
Abstract

A ray-tracing method inspired by ergodic billiards is used to estimate the theoretically best decision rule for a given set of linear separable examples. For randomly distributed examples, the billiard estimate of the single Perceptron with best average generalization probability agrees with known analytic results, while for real-life classification problems, the generalization probability is consistently enhanced when compared to the maximal stability Perceptron.