Dear SVM'ers (and perhaps also SRM'ers and VC'ers),

Hi.  I e-mail you now for essentially two main reasons.

One is to mention the existence of a postdoc. fellowship here at Monash
University in Melbourne, Australia for 2009 with a rapidly approaching
deadline.  To be eligible, applicants must have had their Ph.D. for
at least approx. two years and at most approx. eight years.

And another is to announce a tribute to Chris Wallace (1933-2004),
whose (Computer J., 1968) paper saw both the beginning of the
(Bayesian) Minimum Message Length (MML) principle and of its use
in MML clustering and mixture modelling.

I'll discuss the Chris Wallace tribute and then the Monash postdocs.

First, re Chris Wallace (1933-2004), the Computer Journal (Oxford Univ.
Press) has now placed online on its WWW site all the articles from the
special issue in honour and memory of C. S. Wallace (1933 - 2004).

The articles are interspersed in various places throughout the list at
http://comjnl.oxfordjournals.org/papbyrecent.dtl , and they include my
  David L. Dowe, "Foreword re C. S. Wallace"
  (www.doi.org : 10.1093/comjnl/bxm117),
in which I attempt to survey Chris Wallace's career and his work,
with a particular focus on (Bayesian) Minimum Message Length [MML]
and achievements.

  Sec. 0.2.2 has a discussion of SVMs using MML or (the much later) MDL.

  For those with an interest in Bayesian nets, discussion of MML
Bayesian networks with decision trees in their internal nodes - a`
la Comley & Dowe (2003) and Comley & Dowe (April 2005, MIT Press)
[http://comjnl.oxfordjournals.org/cgi/content/full/bxm117#BXM117C64
www.csse.monash.edu.au/~dld/David.Dowe.publications.html#ComleyDowe2003
and
www.csse.monash.edu.au/~dld/David.Dowe.publications.html#ComleyDowe2005
http://comjnl.oxfordjournals.org/cgi/content/full/bxm117#BXM117C65]
- takes place in sec. 0.2.5.
  For those with a particular interest in (MML) neural nets, see, e.g.,
http://comjnl.oxfordjournals.org/cgi/content/full/bxm117#BXM117C165 .

  Footnote 18 (http://comjnl.oxfordjournals.org/cgi/content/full/bxm117#FN18)
gives examples of corrections to papers (and their coding schemes)
where claims have been made - based on a variety of not-so-good
coding schemes - that MML/MDL doesn't work.
  And anyone struggling to get the difference between Maximum A
Posteriori (MAP) and MML is referred to footnote 158
(http://comjnl.oxfordjournals.org/cgi/content/full/bxm117#FN158).

And, amidst the surveying, there is some new original work there, too.
Some of this includes my note on probabilistic classification, footnote
175 (http://comjnl.oxfordjournals.org/cgi/content/full/bxm117#FN175),
which gives an apparent uniqueness result suggesting advantages and
merits of log-loss over the likes of Area Under Curve (AUC) and ROC, etc.
And all of the technical points in the ad below for the postdoc.
fellowship also get at least a mention and some (quite) a discussion.

2009 Monash (University) Fellowships
------------------------------------
And, last, re postdocs, David Dowe is looking for a postdoctoral fellow
for collaborative work on (Bayesian) Minimum Message Length (MML)
(and/or Kolmogorov complexity) applied to any of (e.g.) support vector
machines (SVMs), structural risk minimisation (SRM), regression,
clustering, mixture modelling, hierarchical clustering and hierarchical
mixture modelling, latent factor analysis, time series, DNA microarray
analysis, decision trees, decision graphs, Bayesian nets, neural nets,
classification, phylogenetic networks (or phylogenetic graphs),
Inductive Logic Programming (ILP) and hybrids thereof, etc.

The postdoc. fellowship(s) is/are at Monash University in Melbourne,
Australia [and the deadline is slowly starting to get a little tight].

The relevant researcher should have between two and eight years
of post-doctoral experience as of September 2008.  A successful
applicant will be appointed as Research Fellow (Level B) beginning
January 2009, with a salary per annum up to Aus$82,951 (including
superannuation) and Aus$50,000 additional research support for 5
years.  More specific and detailed information is at
www.csse.monash.edu.au/~dld/2009_DDowe_MML_MonashFellowships-guidelines.pdf
(or is obtainable from David Dowe by e-mailing to me (David Dowe)
[and not to the list]).

The stated University deadline is Tuesday 5 August 2008, but Monash
University's Faculty of I.T. will quite possibly have a much earlier
internal deadline of approx. 1ish or 2ish weeks earlier - so we should
try to aim for that.  I would welcome any help you can provide in
helping me to find a prospective applicant.

If you are interested in applying for the abovementioned postdoc.,
please e-mail me, David Dowe, directly with a c.v., any questions
and comments.


Cheers, yours faithfully and best wishes,

David Dowe (www.csse.monash.edu.au/~dld).