Algorithmic Probability and Friends. Bayesian Prediction and Artificial Intelligence : Papers From the Ray Solomonoff 85th Memorial Conference, Melbourne, VIC, Australia, November 30 -- December 2, 2011

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. Front Matter....Pages - Introduction to Ray Solomonoff 85th Memorial Conference....Pages 1-36 Ray Solomonoff and the New Probability....Pages 37-52 Universal Heuristics: How Do Humans Solve “Unsolvable” Problems?....Pages 53-54 Partial Match Distance....Pages 55-64 Falsification and Future Performance....Pages 65-78 The Semimeasure Property of Algorithmic Probability – “Feature” or “Bug”?....Pages 79-90 Inductive Inference and Partition Exchangeability in Classification....Pages 91-105 Learning in the Limit: A Mutational and Adaptive Approach....Pages 106-118 Algorithmic Simplicity and Relevance....Pages 119-130 Categorisation as Topographic Mapping between Uncorrelated Spaces....Pages 131-141 Algorithmic Information Theory and Computational Complexity....Pages 142-154 A Critical Survey of Some Competing Accounts of Concrete Digital Computation....Pages 155-173 Further Reflections on the Timescale of AI....Pages 174-183 Towards Discovering the Intrinsic Cardinality and Dimensionality of Time Series Using MDL....Pages 184-197 Complexity Measures for Meta-learning and Their Optimality....Pages 198-210 Design of a Conscious Machine....Pages 211-222 No Free Lunch versus Occam’s Razor in Supervised Learning....Pages 223-235 An Approximation of the Universal Intelligence Measure....Pages 236-249 Minimum Message Length Analysis of the Behrens–Fisher Problem....Pages 250-260 MMLD Inference of Multilayer Perceptrons....Pages 261-272 An Optimal Superfarthingale and Its Convergence over a Computable Topological Space....Pages 273-284 Diverse Consequences of Algorithmic Probability....Pages 285-298 An Adaptive Compression Algorithm in a Deterministic World....Pages 299-305 Toward an Algorithmic Metaphysics....Pages 306-317 Limiting Context by Using the Web to Minimize Conceptual Jump Size....Pages 318-326 Minimum Message Length Order Selection and Parameter Estimation of Moving Average Models....Pages 327-338 Abstraction Super-Structuring Normal Forms: Towards a Theory of Structural Induction....Pages 339-350 Locating a Discontinuity in a Piecewise-Smooth Periodic Function Using Bayes Estimation....Pages 351-365 On the Application of Algorithmic Probability to Autoregressive Models....Pages 366-385 Principles of Solomonoff Induction and AIXI....Pages 386-398 MDL/Bayesian Criteria Based on Universal Coding/Measure....Pages 399-410 Algorithmic Analogies to Kamae-Weiss Theorem on Normal Numbers....Pages 411-416 (Non-)Equivalence of Universal Priors....Pages 417-425 A Syntactic Approach to Prediction....Pages 426-438 Developing Machine Intelligence within P2P Networks Using a Distributed Associative Memory....Pages 439-443 Back Matter....Pages - 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 above mentioned topics in tribute to Ray Solomonoff and his legacy