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...

Täydet tiedot

Bibliografiset tiedot

Julkaisussa:	Artificial intelligence. 106, 2 (1998).
Päätekijä:	Bylander, Tom
Aineistotyyppi:	Artikkeli
Kieli:	English
Aiheet:	Learning algorithms. Absolute loss bounds. Mistake bounds. Randomized classification algorithms.