Algorithmic Probability and Friends
Bayesian Prediction and Artificial Intelligence
Papers from the Ray Solomonoff 85th Memorial Conference Melbourne, VIC, Australia, November / December 2011
David L. Dowe (Ed.)
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.
Introduction to Ray Solomonoff 85th Memorial Conference - Dowe, David L. Seiten 1-36
Ray Solomonoff and the New Probability - Solomonoff, Grace Seiten 37-52
Universal Heuristics: How Do Humans Solve “Unsolvable” Problems? - Levin, Leonid A. Seiten 53-54
Partial Match Distance - Li, Ming Seiten 55-64
Falsification and Future Performance - Balduzzi, David Seiten 65-78
The Semimeasure Property of Algorithmic Probability – “Feature” or “Bug”? - Campbell, Douglas Seiten 79-90
Inductive Inference and Partition Exchangeability in Classification - Corander, Jukka (et al.) Seiten 91-105
Learning in the Limit: A Mutational and Adaptive Approach - Inojosa da Silva Filho, Reginaldo (et al.) Seiten 106-118
Algorithmic Simplicity and Relevance - Dessalles, Jean-Louis Seiten 119-130
Categorisation as Topographic Mapping between Uncorrelated Spaces - Ellison, T. Mark Seiten 131-141
Algorithmic Information Theory and Computational Complexity - Freivalds, Rusinš Seiten 142-154
A Critical Survey of Some Competing Accounts of Concrete Digital Computation - Fresco, Nir Seiten 155-173
Further Reflections on the Timescale of AI - Hall, J. Storrs Seiten 174-183
Towards Discovering the Intrinsic Cardinality and Dimensionality of Time Series Using MDL - Hu, Bing (et al.) Seiten 184-197
Complexity Measures for Meta-learning and Their Optimality - Jankowski, Norbert Seiten 198-210
Design of a Conscious Machine - King, P. Allen Seiten 211-222
No Free Lunch versus Occam’s Razor in Supervised Learning - Lattimore, Tor (et al.) Seiten 223-235
An Approximation of the Universal Intelligence Measure - Legg, Shane (et al.) Seiten 236-249
Minimum Message Length Analysis of the Behrens–Fisher Problem - Makalic, Enes (et al.) Seiten 250-260
MMLD Inference of Multilayer Perceptrons - Makalic, Enes (et al.) Seiten 261-272
An Optimal Superfarthingale and Its Convergence over a Computable Topological Space - Miyabe, Kenshi Seiten 273-284
Diverse Consequences of Algorithmic Probability - Özkural, Eray Seiten 285-298
An Adaptive Compression Algorithm in a Deterministic World - Pelckmans, Kristiaan Seiten 299-305
Toward an Algorithmic Metaphysics - Petersen, Steve Seiten 306-317
Limiting Context by Using the Web to Minimize Conceptual Jump Size - Rzepka, Rafal (et al.) Seiten 318-326
Minimum Message Length Order Selection and Parameter Estimation of Moving Average Models - Schmidt, Daniel F. Seiten 327-338
Abstraction Super-Structuring Normal Forms: Towards a Theory of Structural Induction - Silvescu, Adrian (et al.) Seiten 339-350
Locating a Discontinuity in a Piecewise-Smooth Periodic Function Using Bayes Estimation - Solomonoff, Alex Seiten 351-365
On the Application of Algorithmic Probability to Autoregressive Models - Solomonoff, Ray J. (et al.) Seiten 366-385
Principles of Solomonoff Induction and AIXI - Sunehag, Peter (et al.) Seiten 386-398
MDL/Bayesian Criteria Based on Universal Coding/Measure - Suzuki, Joe Seiten 399-410
Algorithmic Analogies to Kamae-Weiss Theorem on Normal Numbers - Takahashi, Hayato Seiten 411-416
(Non-)Equivalence of Universal Priors - Wood, Ian (et al.) Seiten 417-425
A Syntactic Approach to Prediction - Woodward, John (et al.) Seiten 426-438
Developing Machine Intelligence within P2P Networks Using a Distributed Associative Memory - Amir, Amiza (et al.) Seiten 439-443
Lecture Notes in Computer Science
Springer, Paperback, english, 444 pages