Worst-case analysis of the perception and exponentiated update algorithms.

The absolute loss is the absolute difference between the desired and predicted outcome. This paper demonstrates worst-case upper bounds on the absolute loss for the Perception learning algorithm and the Exponentiated Update learning algorithm, which is related to the Weighted Majority algorithm. The...

Cijeli opis

Bibliografski detalji

Izdano u:	Artificial intelligence. 106, 2 (1998).
Glavni autor:	Bylander, Tom
Format:	Članak
Jezik:	English
Teme:	Learning algorithms. Absolute loss bounds. Mistake bounds. Randomized classification algorithms.