Advisory Board

Professor Marcus Hutter

The KurzweilAI.net article Hutter Prize for Lossless Compression of Human Knowledge said

Marcus Hutter has announced the 50,000 Euro Hutter Prize for Lossless Compression of Human Knowledge by compressing the 100MB file Wikipedia ‘enwik8’ file to less than the current record of 18MB.
 
The intent of this prize is to encourage development of intelligent compressors/programs.
 
“Being able to compress well is closely related to intelligence,” says the Prize for Compressing Human Knowledge” website.
 
“While intelligence is a slippery concept, file sizes are hard numbers. Wikipedia is an extensive snapshot of Human Knowledge. If you can compress the first 100MB of Wikipedia better than your predecessors, you(r compressor) likely has to be smart(er).”

Marcus Hutter, Ph.D. (physics), Habil (informatics), runs the 50,000 € Hutter Prize for Compressing Human Knowledge. He is an Associate Professor in the Research School of Information Sciences and Engineering (RSISE) at the Australian National University (ANU) in Canberra, Australia, and senior research in the National Information and Communication Technology of Australia (NICTA). He is also honorary lecturer at Technical University Munich. His current interests are centered around reinforcement learning, algorithmic information theory and statistics, universal induction schemes, adaptive control theory, and related areas.
 
Marcus Hutter authored the book Universal Artificial Intelligence in which he develops a parameter-free theory of an optimal reinforcement learning agent embedded in an arbitrary unknown environment, based on a formal mathematical definition of general intelligence. He also authored Fitness Uniform Selection to Preserve Genetic Diversity, Instantons in QCD: Theory and Application of the Instanton Liquid Model, Robust Estimators under the Imprecise Dirichlet Model, and The Fastest and Shortest Algorithm for All Well-Defined Problems.
 
He coauthored Hybrid Rounding Techniques for Knapsack Problems, Adaptive Online Prediction by Following the Perturbed Leader, Asymptotics of Discrete MDL for Online Prediction, Distribution of Mutual Information from Complete and Incomplete Data, Optimality of Universal Bayesian Sequence Prediction for General Loss and Alphabet, and Family Structure from Periodic Solutions of an Improved Gap Equation. Read his full list of publications! Learn about his lectures.
 
He is reviewer for the journals IEEE-TPAMI, IEEE-TIT, IEEE-SMC, IEEE-TEC, JCSS, MLJ, JMLR, M&M, IPL, IJAR, and Algorithmica. He is reviewer for the conferences COLT, ALT, ICANN, Benelearn, and ACC. He is coorganizer of the UL&OS Workshop, Kolmogorov Seminar, and the Theory Reading Group. He invented patent Image enhancement and post-antialiasing algorithms.
 
Marcus earned a Bachelors degree in computer science in 1989, a Bachelors degree in Physics in 1990, and a Masters degree in computer science in 1992 at the Technical University in Munich, Germany. He earned a PhD in theoretical particle physics there in 1995. In 2003 he completed his Habilitation (2nd PhD) at the Technical University Munich in Optimal Sequential Decisions based on Algorithmic Probability, and has since then been an honorary official lecturer there.
 
Read IQ test for AI devices gets experts thinking and Diversity trumps fitness.