## The p-recursive piecewise polynomial sigmoid generators and first-order algorithms for multilayer tanh-like neurons

- Khamron Sunat, Chidchanok Lursinsap, Chee-Hung Henry Chu
- Neural Computing and Applications
- 2006

Highly Influenced

@article{Rujan1997PlayingBI, title={Playing Billiards in Version Space}, author={Pal Rujan}, journal={Neural Computation}, year={1997}, volume={9}, pages={99-122} }

- Published 1997 in Neural Computation
DOI:10.1162/neco.1997.9.1.99

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.