Abstract

Is the universe computable? If so, it may be much cheaper in terms of information requirements to compute all computable universes instead of just ours. I apply basic concepts of Kolmogorov complexity theory to the set of possible universes, and chat about perceived and true randomness, life, generalization, and learning in a given universe. Preliminaries Assumptions. A long time ago, the Great Programmer wrote a program that runs all possible universes on His Big Computer. “Possible ” means “computable”: (1) Each universe evolves on a discrete time scale. (2) Any universe’s state at a given time is describable by a finite number of bits. One of the many universes is ours, despite some who evolved in it and claim it is incomputable. Computable universes. Let TM denote an arbitrary universal Turing machine with unidirectional output tape. TM’s input and output symbols are “0”, “1”, and “, ” (comma). TM’s possible input programs can be ordered

Citations

396	Three approaches to the quantitative definition of information - Kolmogorov - 1968
316	A Formal Theory of Inductive Inference - Solomonoff - 1964
264	Algorithmic Information Theory - Chaitin - 1987
103	The lack of a priori distinctions between learning algorithms - Wolpert - 1996
86	Randomness conservation inequalities: Information and independence in mathematical theories - Levin - 1984
58	Shifting inductive bias with success-story algorithm, adaptive Levin search, and incremental selfimprovement - Schmidhuber, Zhao, et al. - 1997
41	Discovering neural nets with low Kolmogorov complexity and high generalization capability - Schmidhuber - 1997
29	A mathematical theory of communication (parts - Shannon - 1948
28	Reinforcement learning with self-modifying policies, in Learning to - Schmidhuber, Zhao, et al. - 1997
20	Laws of information (nongrowth) and aspects of the foundation of probability theory - Levin - 1974