Algorithmic Probability and Friends. Bayesian Prediction and Artificial Intelligence

1. Long Papers

   1. MMLD Inference of Multilayer Perceptrons

      • Enes Makalic, Lloyd Allison

      Pages 261-272

   2. An Optimal Superfarthingale and Its Convergence over a Computable Topological Space

      • Kenshi Miyabe

      Pages 273-284

   3. Diverse Consequences of Algorithmic Probability

      • Eray Özkural

      Pages 285-298

   4. An Adaptive Compression Algorithm in a Deterministic World

      • Kristiaan Pelckmans

      Pages 299-305

   5. Toward an Algorithmic Metaphysics

      • Steve Petersen

      Pages 306-317

   6. Limiting Context by Using the Web to Minimize Conceptual Jump Size

      • Rafal Rzepka, Koichi Muramoto, Kenji Araki

      Pages 318-326

   7. Minimum Message Length Order Selection and Parameter Estimation of Moving Average Models

      • Daniel F. Schmidt

      Pages 327-338

   8. Abstraction Super-Structuring Normal Forms: Towards a Theory of Structural Induction

      • Adrian Silvescu, Vasant Honavar

      Pages 339-350

   9. Locating a Discontinuity in a Piecewise-Smooth Periodic Function Using Bayes Estimation

      • Alex Solomonoff

      Pages 351-365

   10. On the Application of Algorithmic Probability to Autoregressive Models

       • Ray J. Solomonoff, Elias G. Saleeby

       Pages 366-385

   11. Principles of Solomonoff Induction and AIXI

       • Peter Sunehag, Marcus Hutter

       Pages 386-398

   12. MDL/Bayesian Criteria Based on Universal Coding/Measure

       • Joe Suzuki

       Pages 399-410

   13. Algorithmic Analogies to Kamae-Weiss Theorem on Normal Numbers

       • Hayato Takahashi

       Pages 411-416

   14. (Non-)Equivalence of Universal Priors

       • Ian Wood, Peter Sunehag, Marcus Hutter

       Pages 417-425

   15. A Syntactic Approach to Prediction

       • John Woodward, Jerry Swan

       Pages 426-438

2. Short Paper

   1. Developing Machine Intelligence within P2P Networks Using a Distributed Associative Memory

      • Amiza Amir, Anang Hudaya M. Amin, Asad Khan

      Pages 439-443

3. Back Matter

   PDF

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