Proceedings Article, Paper
@InProceedings
Beitrag in Tagungsband, Workshop


Show entries of:

this year (2019) | last year (2018) | two years ago (2017) | Notes URL

Action:

login to update

Options:








Author, Editor

Author(s):

Jaeger, Manfred

dblp



Editor(s):

Fawcett, Tom
Mishra, Nina

dblp
dblp

Not MPII Editor(s):

Fawcett, Tom
Mishra, Nina

BibTeX cite key*:

JaegerICML03

Title, Booktitle

Title*:

Probabilistic Classifiers and the Concepts they Recognize

Booktitle*:

Proceedings of the Twentieth International Conference on Machine Learning (ICML-03)

Event, URLs

URL of the conference:

http://www.hpl.hp.com/conferences/icml03/

URL for downloading the paper:


Event Address*:

Washington DC, U.S.

Language:

English

Event Date*
(no longer used):

August 21-24, 2003

Organization:


Event Start Date:

21 August 2003

Event End Date:

24 August 2003

Publisher

Name*:

AAAI Press

URL:

http://www.aaai.org/Press/press.html

Address*:

Menlo Park, USA

Type:


Vol, No, Year, pp.

Series:


Volume:


Number:


Month:


Pages:

266-273

Year*:

2003

VG Wort Pages:


ISBN/ISSN:

0-1-57735-189-4

Sequence Number:


DOI:




Note, Abstract, ©


(LaTeX) Abstract:

We investigate algebraic, logical, and geometric
properties of concepts recognized by various classes
of probabilistic classifiers. For this we introduce a
natural hierarchy of probabilistic classifiers, the
lowest level of which comprises the naive Bayesian
classifiers. We show that the expressivity of classifiers on the
different levels in the hierarchy is characterized
algebraically by separability with polynomials of
different degrees. A consequence of this result is that
every linearly separable concept can be recognized by a
naive Bayesian classifier. We contrast this result with
negative results about the naive Bayesian classifier
previously reported in the literature, and point out that
these results only pertain to specific learning
scenarios for naive Bayesian classifiers. We also present
some logical and geometric characterizations of linearly
separable concepts, thus providing additional intuitive
insight into what concepts are recognizable by naive
Bayesian classifiers.



Download
Access Level:

Public

Correlation

MPG Unit:

Max-Planck-Institut für Informatik



MPG Subunit:

Programming Logics Group

Audience:

popular

Appearance:

MPII WWW Server, MPII FTP Server, MPG publications list, university publications list, working group publication list, Fachbeirat, VG Wort



BibTeX Entry:

@INPROCEEDINGS{JaegerICML03,
AUTHOR = {Jaeger, Manfred},
EDITOR = {Fawcett, Tom and Mishra, Nina},
TITLE = {Probabilistic Classifiers and the Concepts they Recognize},
BOOKTITLE = {Proceedings of the Twentieth International Conference on Machine Learning (ICML-03)},
PUBLISHER = {AAAI Press},
YEAR = {2003},
PAGES = {266--273},
ADDRESS = {Washington DC, U.S.},
ISBN = {0-1-57735-189-4},
}


Entry last modified by Viorica Sofronie-Stokkermans, 03/12/2010
Show details for Edit History (please click the blue arrow to see the details)Edit History (please click the blue arrow to see the details)
Hide details for Edit History (please click the blue arrow to see the details)Edit History (please click the blue arrow to see the details)

Editor(s)
Manfred Jaeger
Created
05/11/2003 03:45:46 PM
Revisions
5.
4.
3.
2.
1.
Editor(s)
Viorica Sofronie-Stokkermans
Sabine Krott
Christine Kiesel
Uwe Brahm
Uwe Brahm
Edit Dates
06/23/2004 02:16:27 PM
22.06.2004 10:19:42
17.06.2004 15:46:32
05/07/2004 07:13:58 PM
06/09/2003 01:15:00 AM
Show details for Attachment SectionAttachment Section
Hide details for Attachment SectionAttachment Section