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.
Full Text 
Sign-in/Register to access full text options
Sign-in/Register to access full text options 
Published version (
Free)
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
