Associate Professor, Clayton School of Information Technology, Monash University

I work primarily in Minimum Message Length (MML) - a unifying tool in machine learning (computer science, artificial intelligence), statistics, econometrics, inductive inference (philosophy of science) and ``data mining''. MML unifies these areas by combining Bayesianism, (algorithmic) information theory and Kolmogorov complexity. MML was first published in Wallace and Boulton (Computer J, 1968) and is relevant whenever data needs to be analysed.

Some of the many areas in which I have applied MML include statistical inference (and model selection and point estimation), prediction, machine learning, econometrics (including time series and panel data), proofs of financial market inefficiency, knowledge discovery, ``data mining'', theories of (quantifying) intelligence and new forms of (universal) intelligence test (for biological and non-biological agents), philosophy of science, the problem of induction, bioinformatics, linguistics (evolutionary [tree] models), image analysis, etc.

My Comley and Dowe (2003, 2005) are the first two papers on MML Bayesian nets which can deal with both discrete (multi-valued) and continuous-valued variables.

Wallace and Dowe (1999a) is the most cited Wallace paper with a co-author still actively working on MML.

In Chris Wallace (1933-2004)'s posthumous ``Statistical and Inductive Inference by Minimum Message Length'' (2005),
(a) I am given special mention in the preface on page vi,
(b) I am the outright most mentioned living person in the table of contents, where my name appears twice,
(c) I am the living person whose name and work are most mentioned in the index,
(d) I am the outright most cited living author.

I am a native English speaker, at least partly competent in both French and (Castillian) Spanish.


  • –present
    Associate Professor (Computer Science, Artificial Intelligence, Machine Learning), Monash University


  • 1991 
    Monash University, PhD (Mathematics)


  • 2011
    "MML, hybrid Bayesian network graphical models, statistical consistency, invariance & uniqueness", Handbook of Philos of Sci (Vol. 7: Handbook of Philosophy of Statistics), Elsevier, pp901-982,
  • 2010
    ``Measuring Universal Intelligence: Towards an Anytime Intelligence Test'', Artificial Intelligence journal, Vol 174, Issue 18, December 2010, pp1508-1539,
  • 2008
    ``Foreword re C. S. Wallace'', Computer Journal, Vol. 51, No. 5 (Sept. 2008), pp523-560,
  • 2007
    ``Bayes Not Bust! Why Simplicity is no problem for Bayesians'', British J. Philosophy of Science, Vol. 58, No. 4, December 2007, pp709 - 754,
  • 2005
    ``Minimum Message Length and Generalised Bayesian Networks with Asymmetric Languages'', Chapter 11 in `Advances in Minimum Description Length: Theory and Applications', MIT Press, April,
  • 2003
    ``General Bayesian Networks and Asymmetric Languages'', Proc. 2nd Hawaii International Conference on Statistics and Related Fields, 5-8 June, 2003,
  • 2000
    ``MML clustering of multi-state, Poisson, von Mises circular and Gaussian distributions'', Statistics and Computing, Vol. 10, No. 1, Jan. 2000, pp73-83,
  • 1999
    ``Minimum Message Length and Kolmogorov Complexity'', Computer Journal, Vol. 42, No. 4, pp270-283,
  • 1998
    ``Kolmogorov complexity, minimum message length and inverse learning'', 14th Australian Statistical Conf' (ASC-14), Broadbeach, Gold Coast, Qld, 6-10 July 1998, p144,

Research Areas

  • Statistical Theory (010405)
  • Coding And Information Theory (080401)
  • Pattern Recognition And Data Mining (080109)
  • Artificial Intelligence And Image Processing Not Elsewhere Classified (080199)
  • Computer Vision (080104)


My paid research invitations include at least twice as an invited conference speaker in the northern hemisphere.

My Wallace & Dowe (1999a) and my Hernandez-Orallo & Dowe (2010) have both been the most downloaded articles in their respective journals.