MML, MDL, Bayes and Kolmogorov paper

Thread View: comp.ai

1 messages

[T] Back to Threads [V] Tree View [G] Group Articles

1 total messages Started by David L Dowe Sun, 27 Dec 1998 00:00

#9071

Author: David L Dowe
Date: Sun, 27 Dec 1998 00:00

25 lines
2132 bytes

   Dear AI and machine learning people,

      Hi.   Just drawing your attention to the fact that the paper
"Minimum Message Length and Kolmogorov Complexity",
by C. S. Wallace and (yours truly) D. L. Dowe,
has been accepted to appear in a special issue of the Computer Journal
(to mark the 30th anniversary of the seminal Wallace and Boulton (1968) paper).


This (14-page) paper discusses connections between the Bayesian information-
theoretic Minimum Message Length (MML) principle and Kolmogorov complexity,
with some mention of Minimum Description Length (MDL).  It also makes passing
mention of Dowe's (1997) conjecture that Bayesian priors are required for
an estimation method to always be both invariant and consistent.


Please e-mail me if you would like me to send postscript (.ps).


David.

Dr. David Dowe, Senior Lecturer, School of Computer Science and Software Eng.,
Monash University, Clayton, Victoria 3168, Australia     dld@cs.monash.edu.au
Tel:+61 3 9905-5776  Fax:+61 3 9905-5146   http://www.csse.monash.edu.au/~dld/

Thread Navigation

This is a paginated view of messages in the thread with full content displayed inline.

Messages are displayed in chronological order, with the original post highlighted in green.

Use pagination controls to navigate through all messages in large threads.

Back to All Threads