Minimum Message Length (MML) work of Wallace (1968) and, relatedly, Solomonoff (1964) and Rissanen (MDL, 1978) gives a unified framework for consistent, efficient and invariant statistical inference.
Some might also call this "machine learning".
The ISIS conference has assembled 4 world leaders in inductive inference and machine learning (Ray Solomonoff, Chris Wallace, Jorma Rissanen and Ross Quinlan). I believe that no 3 of these 4 people have ever been assembled together before. Others presenting at the conference include Marvin Minsky (Turing Award winner, I believe) and Henry Kyburg.
Also present will be people with many classical approaches to statistics and "machine learning".
Information about ISIS, the technical program and the registration costs are below.
Please forward this call on to interested parties.
ISIS CONFERENCE: INFORMATION, STATISTICS AND INDUCTION IN SCIENCE
Old Melbourne Hotel Melbourne, Australia 20-23 August 1996
Henry Kyburg, Jr. (University of Rochester, NY) Marvin Minsky (MIT) J. Ross Quinlan (Sydney University) Jorma J. Rissanen (IBM Almaden Research, San Jose, California) Ray Solomonoff (Oxbridge Research, Mass)
This conference will explore the use of computational modeling to understand and emulate inductive processes in science. The problems involved in building and using such computer models reflect methodological and foundational concerns common to a variety of academic disciplines, especially statistics, artificial intelligence (AI) and the philosophy of science. This conference aims to bring together researchers from these and related fields to present new computational technologies for supporting or analysing scientific inference and to engage in collegial debate over the merits and difficulties underlying the various approaches to automating inductive and statistical inference.
About the invited speakers:
Henry Kyburg is noted for his invention of the lottery paradox (in "Probability and the Logic of Rational Belief", 1961) and his research since then in providing a non-Bayesian foundation for a probabilistic epistemology.
Marvin Minsky is one of the founders of the field of artificial intelligence. He is the inventor of the use of frames in knowledge representation, stimulus for much of the concern with nonmonotonic reasoning in AI, noted debunker of Perceptrons and recently the developer of the "society of minds" approach to cognitive science.
J. Ross Quinlan is the inventor of the information-theoretic approach to classification learning in ID3 and C4.5, which have become world-wide standards in testing machine learning algorithms.
Jorma J. Rissanen invented the Minimum Description Length (MDL) method of inference in 1978, which has subsequently been widely adopted in algorithms supporting machine learning.
Ray Solomonoff developed the notion of algorithmic complexity in 1960, and his work was influential in shaping the Minimum Message Length (MML) work of Chris Wallace (1968) and the Minimum Description Length (MDL) work of Jorma Rissanen (1978).
========================= Tutorials (Tue 20 Aug 96) =========================
10am - 1pm: Tutorial 1: Peter Spirtes "Automated Learning of Bayesian Networks" Tutorial 2: Michael Pazzani "Machine Learning and Intelligent Info Access" 2pm - 5pm: Tutorial 3: Jan Zytkow "Automation of Scientific Discovery" Tutorial 4: Paul Vitanyi "Kolmogorov Complexity & Applications"
About the tutorial leaders:
Peter Spirtes is a co-author of the TETRAD algorithm for the induction of causal models from sample data and is an active member of the research group on causality and induction at Carnegie Mellon University.
Michael Pazzani is one of the leading researchers world-wide in machine learning and the moderator of ML-LIST, an electronic mailing list on Machine Learning. Current interests include the use of intelligent agents to support information filtering over the Internet.
Jan Zytkow is one of the co-authors (with Simon, Langley and Bradshaw) of "Scientific Discovery" (1987), reporting on the series of BACON programs for automating the learning of quantitative scientific laws.
Paul Vitanyi is co-author (with Ming Li) of "An Introduction to Kolmogorov Complexity and its Applications (1993) and of much related work on complexity and information-theoretic methods of induction. Professor Vitanyi will be visiting the Department of Computer Science, Monash, for several weeks after the conference.
A limited number of free student conference registrations or tutorial registrations will be available by application to the organizers in exchange for part-time work during the conference.
Program Committee: Hirotugu Akaike, Lloyd Allison, Shun-Ichi Amari, Mark Bedau, Jim Bezdek, Hamparsum Bozdogan, Wray Buntine, Peter Cheeseman, Honghua Dai, David Dowe, Usama Fayyad, Doug Fisher, Alex Gammerman, Clark Glymour, Randy Goebel, Josef Gruska, David Hand, Bill Harper, David Heckerman, Colin Howson, Lawrence Hunter, Frank Jackson, Max King, Kevin Korb, Henry Kyburg, Rick Lathrop, Ming Li, Nozomu Matsubara, Aleksandar Milosavljevic, Richard Neapolitan, Jon Oliver, Michael Pazzani, J. Ross Quinlan, Glenn Shafer, Peter Slezak, Padhraic Smyth, Ray Solomonoff, Paul Thagard, Neil Thomason, Raul Valdes-Perez, Tim van Gelder, Paul Vitanyi, Chris Wallace, Geoff Webb, Xindong Wu, Jan Zytkow.
Inquiries to: firstname.lastname@example.org David Dowe (chair): email@example.com Kevin Korb (co-chair): firstname.lastname@example.org or Jonathan Oliver (co-chair): email@example.com
- David Dowe. =======================================================================
ISIS: Information, Statistics and Induction in Science
SCHEDULE OF EVENTS
Tuesday 20/8/1996 Tutorials - see above.
9.30am-10.30am Invited Talk: J. Ross Quinlan (Sydney University): "First-Order Induction: Techniques and Applications"
10.30am-11am Morning Break
Classification Trees, Graphs and Rules: I
11am-11.30am Hong, S.J ., Hosking, J.R.M., & Winograd, S. "Use of Randomization to Normalize Feature Merits" 11.30am-12pm Webb, G.I. "A Heuristic Covering Algorithm has Higher Predictive Accuracy Than Learning all the Rules" 12pm-12.30pm Pearson, R.A. "Single Pass Constructive Induction with Continuous Variables" 12.30pm-1pm Cleary, J. G. , Legg, S., & Witten, I.H. "An MDL Estimate of the Significance of Rules"
Classification Trees, Graphs and Rules: II
2pm-2.30pm Karalic, A. "Producing More Comprehensible Models While Retaining Their Performance" 2.30pm-3pm Pazzani, M.J. "Constructive Induction of Cartesian Product Attributes" 3pm-3.30pm Neil, J.R., & Korb, K.B. "The MML Evolution of Classification Graphs"
3.30pm-4pm Afternoon Break
4pm-5pm Invited Talk: Jorma J. Rissanen (IBM): "A Universal Regression Model"
5pm-5.30pm Laskar, M.R., & King, M.L. "Estimation of Regression Disturbances Based on Minimum Message Length" 5.30pm-6pm Legg, S. "Minimum Information Estimation of Linear Regression Models"
Foundations of Statistics: I
9.30am-10am Kabaila, P. "The Evaluation of Model Selection Criteria: Pointwise Limits in the Parameter Space" 10am-10.30am Dollinger, M.B., Kulinskaya, E., & Staudte, R.G. "Fuzzy Hypothesis Tests and Confidence Intervals"
10.30am-11am Morning Break
11am-12am Invited Talk: Marvin Minsky (MIT): "Discovering Theories of Discovering"
Foundations of Statistics: II
12pm-12.30pm Amati, G., van Rijsbergen, K., Ubaldini, F. "The Maximum Expected Utility Principle: The Case Study of Information Retrieval" 12.30pm-1pm Pandya, R., & Galton, A. "Multi-Layer Thinking in Logic and Probability"
Stream 1: Biology
2pm-2.30pm Cruz, G.P.A., & Beliakov, G. "Fuzzy Gating and Its Application in Flow Cytometry" 2.30pm-3pm Corruble, V. "Induction in Medical Discovery: A Computational Simulation" 3pm-3.30pm Tsumoto, S., & Tanaka, H. "Comparative Analysis of Amino Acid Sequences of Proteins Using Rough Sets and Change of Representation"
4pm-4.30pm Tanaka, H., Ren, F., & Fukuda, N. "Minimum Complexity Principle and its Application to Reconstruction of Molecular Phylogenetic Tree"
Stream 1: Economics
4.30pm-5pm Chen S.H., & Tan, C.W. "Measuring Randomness by Rissanen's Stochastic Complexity: Applications to the Financial Data" 5pm-5.30pm Dowe D.L. & Korb, K.B. "Conceptual Difficulties with the Efficient Market Hypothesis: Towards a Naturalized Economics"
Stream 2: Philosophy of AI
2pm-2.30pm Dowe, P. "Chance Lowering Causes: Old Problems for New Versions of the Probablistic Theory of Causation" 2.30pm-3pm Dorin, A. "Computer Based Life, Possibilities and Impossibilities" 3pm-3.30pm Korb, K.B. "Symbolicism and Connectionism: AI Back at a Join Point"
Stream 2: Scientific Discovery
4pm-4.30pm Bulmer, M. "Inductive Theories from Equational Systems" 4.30pm-5pm Zytkow, J.M. "From Statistical Regularities to Concepts, Hierarchies, Equation Clusters and Rules" 5pm-5.30pm Patrick, J. "A Minimum Message Length (MML) Model for Software Measures"
Minimum Encoding Inference: I
9.30am-10am VitÃ¡nyi, P. & Li, M. "Ideal MDL and Its Relation to Bayesianism" 10am-10.30am Baxter, R.A. "The Likelihood Principle and MML Estimators"
10.30am-11am Morning Break
11am-12am Invited Talk: Henry Kyburg , Jr. (University of Rochester): "Bayesian Inference and Inductive Inference"
Minimum Encoding Inference: II
12pm-12.30pm Wallace, C.S. "False Oracles and Strict MML Estimators" 12.30pm-1pm Hulme, M.R. "An Analysis of SMML from a Subjective Bayesian Perspective"
Mixture Modeling: I
2pm-2.30pm Li, W.Q., Attikouzel, Y., & Bezdek, J.C. "Estimating the Number of Components in a Normal Mixture" 2.30pm-3pm Upal, M.A. "Comparison of Unsupervised Classifiers" 3pm-3.30pm McLachlan, G.J., & Peel, D. "An Algorithm for Unsupervised Learning via Normal Mixture Models"
4pm-5pm Invited Talk: Ray Solomonoff (Oxbridge Research) "Does Algorithmic Probability Solve the Problem of Induction?"
Mixture Modeling: II
5pm-5.30pm Kontkanen, P.T., MyllymÃ¤ki, P.J. & Tirri, H.R. "Comparing Bayesian Model Class Selection Criteria by Discrete Finite MIxtures" 5.30pm-6pm Jorgensen, M. A., Hunt, L.A. "Mixture Model Clustering of Data Sets with Categorical and Continuous Variables"
Accommodation ------------- Old Melbourne Hotel single (side street room) @ $ 126/night ___________ single (courtyard room) @ $ 136/night ___________ double (side street) @ $ 71/night/person ___________ double (courtyard) @ $ 76/night/person ___________
Arrival date ___/Aug/96 Departure date ___/Aug/96
Number of Night(s) ____
If sharing with another conference attendee, please enter that person's
______Conference Dinners @ $ 50 ea ___________
______Extra Proceedings @ $ 60 ea ___________
Prices are stated in AUS$. You may pay by cheque in US$ by deducting 15% from the Australian prices (if you don't like the implicit exchange rate, please send Australian dollars or pay by credit card). Credit Card charges will be in AUS$ and charged at the current exchange rate. We accept Visa and Master Card.
Payment: Cheque or Money Order (made out to: Monash University) or Credit Card (MasterCard or Visa):
Name on Credit Card ______________________________
Credit Card Number ______________________________
Expiry Date ______________
Withdrawals and cancellations must be received in writing by 1 Aug 1996, and will be subject to a fee of AUS $50. After this date no refunds will be made.
* Proof of student status is required, such as a letter from your department.