DM: Workshop on Minimum Length Encoding

[AI97]

                         CALL FOR PARTICIPATION
==============================================================================

Half-day tutorial:  Introduction to Minimum Length Encoding Inference
==============================================================================

Monday 1st December (Morning) 
Rendevous Observation City Hotel
Scarborough, Western Australia

Held in ocnjunction with the Australian Joint conference on 
Artificial 
Intelligencde 1997, 2-4 December 

http://www.cs.curtin.edu.au/~ai97
email: ai97@cs.curtin.edu.au

This tutorial is of interest to anyone who analyses data in various 
forms.
This includes scientists interested in machine learning, data mining 
and those
interested an a broad range of applications from portfolio fund 
managers to
companies wishing to determine where best to mine for minerals or 
oil, etc.

The tutorial will be on Minimum Length Encoding, encompassing both 
Minimum Message Length (MML) and Minimum Description Length (MDL) 
inductive
inference. This work is information-theoretic in nature, with a broad 
range of applications in machine learning, statistics, "knowledge 
discovery" and "data mining".
We discuss statistical parameter estimation, mixture modelling (or 
clustering) of continuous, discrete and circular data, learning 
decision trees and finite state
machines, inductive (constraint) logic programming, and possibly 
other problems if time permits. Some of these machine learning 
techniques will then be applied to
real-world problems, such as protein structure prediction and the 
human genome project, lossless image compression, exploration 
geology, business forecasting,
market inefficiency and natural language. Passing mention will be 
made of foundational issues such as connections to 
Kolmogorov-Solomonoff complexity, universal
modelling and (probabilistic) prediction. There will be some 
flexibility in the depth and scope of material presented depending 
upon the preferences of the attendees.

Presenter

David Dowe 
     email: dld@cs.monash.edu.au 
     WWW: http://www.cs.monash.edu.au/~dld/