Skip navigation
Skip navigation

Limits of learning about a categorical latent variable under prior near-ignorance

Piatti, Alberto; Zaffalon, Marco; Trojani, Fabio; Hutter, Marcus

Description

In this paper, we consider the coherent theory of (epistemic) uncertainty of Walley, in which beliefs are represented through sets of probability distributions, and we focus on the problem of modeling prior ignorance about a categorical random variable. In this setting, it is a known result that a state of prior ignorance is not compatible with learning. To overcome this problem, another state of beliefs, called near-ignorance, has been proposed. Near-ignorance resembles ignorance very closely,...[Show more]

CollectionsANU Research Publications
Date published: 2009-04
Type: Journal article
URI: http://hdl.handle.net/1885/14965
Source: International Journal of Approximate Reasoning
DOI: 10.1016/j.ijar.2008.08.003

Download

File Description SizeFormat Image
Piatti et al Limits of Learning about a Categorical Latent Variable 2009.pdf308.93 kBAdobe PDFThumbnail


Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.

Updated:  12 November 2018/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator