A Computer Scientist's View of Life, the Universe, and Everything
Juergen Schmidhuber

TL;DR
This paper explores the computability of the universe using Kolmogorov complexity, discussing randomness, life, and learning in the context of possible universes and their information requirements.
Contribution
It applies Kolmogorov complexity theory to analyze the universe's computability and discusses implications for randomness, life, and learning.
Findings
Computing all possible universes may be more efficient than computing just ours.
The universe's randomness can be perceived or true, affecting its complexity.
Insights into how life and learning relate to universe computability.
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.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsSpace Science and Extraterrestrial Life
The reference list from the paper itself. Each links out to its DOI / PubMed record.
- 1[1] G.J. Chaitin. Algorithmic Information Theory . Cambridge University Press, Cambridge, 1987.
- 2[2] A.N. Kolmogorov. Three approaches to the quantitative definition of information. Problems of Information Transmission , 1:1–11, 1965.
- 3[3] L. A. Levin. Laws of information (nongrowth) and aspects of the foundation of probability theory. Problems of Information Transmission , 10(3):206–210, 1974.
- 4[4] L. A. Levin. Randomness conservation inequalities: Information and independence in mathematical theories. Information and Control , 61:15–37, 1984.
- 5[5] J. Schmidhuber. Discovering neural nets with low Kolmogorov complexity and high generalization capability. Neural Networks , 1997. In press.
- 6[6] J. Schmidhuber, J. Zhao, and N. Schraudolph. Reinforcement learning with self-modifying policies. In S. Thrun and L. Pratt, editors, Learning to learn . Kluwer, 1997. To appear.
- 7[7] J. Schmidhuber, J. Zhao, and M. Wiering. Shifting inductive bias with success-story algorithm, adaptive Levin search, and incremental self-improvement. Machine Learning , 26, 1997. In press.
- 8[8] C. E. Shannon. A mathematical theory of communication (parts I and II). Bell System Technical Journal , XXVII:379–423, 1948.
