Apple tasting and nearly one-sided learning

In the standard on-line model the learning algorithm tries to minimize the total number of mistakes made in a series of trials. On each trial the learner sees an instance, either accepts or rejects that instance, and then is told the appropriate response. The authors define a natural variant of this...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Helmbold, D.P., Littlestone, N., Long, P.M.
Format:	Tagungsbericht
Sprache:	eng
Schlagworte:	Computer science Feedback Loss measurement National electric code Predictive models Sampling methods
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!