Algorithmic Probability and Friends. Bayesian Prediction and Artificial Intelligence

1. Front Matter

   PDF

2. Introduction

   1. Introduction to Ray Solomonoff 85th Memorial Conference

      • David L. Dowe

      Pages 1-36

3. Invited Papers

   1. Ray Solomonoff and the New Probability

      • Grace Solomonoff

      Pages 37-52

   2. Universal Heuristics: How Do Humans Solve “Unsolvable” Problems?

      • Leonid A. Levin

      Pages 53-54

   3. Partial Match Distance

      • Ming Li

      Pages 55-64

4. Long Papers

   1. Falsification and Future Performance

      • David Balduzzi

      Pages 65-78

   2. The Semimeasure Property of Algorithmic Probability – “Feature” or “Bug”?

      • Douglas Campbell

      Pages 79-90

   3. Inductive Inference and Partition Exchangeability in Classification

      • Jukka Corander, Yaqiong Cui, Timo Koski

      Pages 91-105

   4. Learning in the Limit: A Mutational and Adaptive Approach

      • Reginaldo Inojosa da Silva Filho, Ricardo Luis de Azevedo da Rocha, Ricardo Henrique Gracini Guiraldelli

      Pages 106-118

   5. Algorithmic Simplicity and Relevance

      • Jean-Louis Dessalles

      Pages 119-130

   6. Categorisation as Topographic Mapping between Uncorrelated Spaces

      • T. Mark Ellison

      Pages 131-141

   7. Algorithmic Information Theory and Computational Complexity

      • Rūsiņš Freivalds

      Pages 142-154

   8. A Critical Survey of Some Competing Accounts of Concrete Digital Computation

      • Nir Fresco

      Pages 155-173

   9. Further Reflections on the Timescale of AI

      • J. Storrs Hall

      Pages 174-183

   10. Towards Discovering the Intrinsic Cardinality and Dimensionality of Time Series Using MDL

       • Bing Hu, Thanawin Rakthanmanon, Yuan Hao, Scott Evans, Stefano Lonardi, Eamonn Keogh

       Pages 184-197

   11. Complexity Measures for Meta-learning and Their Optimality

       • Norbert Jankowski

       Pages 198-210

   12. Design of a Conscious Machine

       • P. Allen King

       Pages 211-222

   13. No Free Lunch versus Occam’s Razor in Supervised Learning

       • Tor Lattimore, Marcus Hutter

       Pages 223-235

   14. An Approximation of the Universal Intelligence Measure

       • Shane Legg, Joel Veness

       Pages 236-249

   15. Minimum Message Length Analysis of the Behrens–Fisher Problem

       • Enes Makalic, Daniel F. Schmidt

       Pages 250-260

Algorithmic probability and friends: Proceedings of the Ray Solomonoff 85th memorial conference is a collection of original work and surveys. The Solomonoff 85th memorial conference was held at Monash University's Clayton campus in Melbourne, Australia as a tribute to pioneer, Ray Solomonoff (1926-2009), honouring his various pioneering works - most particularly, his revolutionary insight in the early 1960s that the universality of Universal Turing Machines (UTMs) could be used for universal Bayesian prediction and artificial intelligence (machine learning). This work continues to increasingly influence and under-pin statistics, econometrics, machine learning, data mining, inductive inference, search algorithms, data compression, theories of (general) intelligence and philosophy of science - and applications of these areas. Ray not only envisioned this as the path to genuine artificial intelligence, but also, still in the 1960s, anticipated stages of progress in machine intelligence which would ultimately lead to machines surpassing human intelligence. Ray warned of the need to anticipate and discuss the potential consequences - and dangers - sooner rather than later. Possibly foremostly, Ray Solomonoff was a fine, happy, frugal and adventurous human being of gentle resolve who managed to fund himself while electing to conduct so much of his paradigm-changing research outside of the university system. The volume contains 35 papers pertaining to the abovementioned topics in tribute to Ray Solomonoff and his legacy.

• Bayesian prediction
• algorithmic information theory
• algorithmic probability
• technological singularity
• universal turing machines

• Faculty of Information Technology, Clayton School of Information Technology, Monash University, Clayton, Australia

  David L. Dowe

Policies and ethics