since 07 November 2024 :

View(s) :

1 (0 ULiège)

Download(s) :

0 (0 ULiège)

References
Facsimile [PDF, 5.5M]

Pseudo Information Divergences Defined on the Family of Specific Probability Distributions

Hiroyuki Shioya and Tsutomu Da-te

p. 375-386

    Abstract

    Several information measures have been used as the criteria in information theory, statistics and various fields of engineering. Especially an information divergence has been well used as the measure of the difference between two probability distributions. In this paper, we propose the pseudo information divergence, which functions as usual information divergence, if two measured probability distributions are in some family of specific distributions. We introduce an example of the pseudo information divergence, and apply it to the problem of training multi-layer perceptrons from the data with the gross error noise.

    Index

    Keywords

    pseudo information divergence, f-divergence, direct on-line learning, multi-layer perceptron, gross error model

    Text

    Download Facsimile [PDF, 5.5M]

    References

    Bibliographical reference

    Hiroyuki Shioya and Tsutomu Da-te, « Pseudo Information Divergences Defined on the Family of Specific Probability Distributions », CASYS, 11 | 2002, 375-386.

    Electronic reference

    Hiroyuki Shioya and Tsutomu Da-te, « Pseudo Information Divergences Defined on the Family of Specific Probability Distributions », CASYS [Online], 11 | 2002, Online since 29 July 2024, connection on 27 December 2024. URL : http://popups.uliege.be/3041-539x/index.php?id=2063

    Authors

    Hiroyuki Shioya

    Muroran Institute of Technology, 27-1 Mizumoto Muroran, 050-8585, Japan

    By this author

    Tsutomu Da-te

    Division of Systems and Information Engineering, Hokkaido University, Kita-13 Nishi-8 Kita-ku Sapporo, 060-8628, Japan

    By this author

    Copyright

    CC BY-SA 4.0 Deed