Skip to main content

Universal Learning Theory

  • 243 Accesses

Abstract

This encyclopedic article gives a mini-introduction into the theory of universal learning, founded by Ray Solomonoff in the 1960s and significantly developed and extended in the last decade. It explains the spirit of universal learning, but necessarily glosses over technical subtleties.

This is a preview of subscription content, access via your institution.

Buying options

Chapter
USD   29.95
Price excludes VAT (USA)
  • DOI: 10.1007/978-1-4899-7687-1_867
  • Chapter length: 10 pages
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
eBook
USD   799.99
Price excludes VAT (USA)
  • ISBN: 978-1-4899-7687-1
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
Hardcover Book
USD   899.99
Price excludes VAT (USA)

Recommended Reading

  • Cilibrasi R, Vitányi PMB (2005) Clustering by compression. IEEE Trans Inf Theory 51(4):1523–1545

    MathSciNet  CrossRef  MATH  Google Scholar 

  • Gaglio M (2007) Universal search. Scholarpedia 2(11):2575

    CrossRef  Google Scholar 

  • Hutter M (2005) Universal Artificial Intelligence: Sequential Decisions Based on Algorithmic Probability. Springer, Berlin

    CrossRef  MATH  Google Scholar 

  • Hutter M (2006) Human knowledge compression prize. Open ended, http://prize.hutter1.net/

  • Hutter M (2007) On universal prediction and Bayesian confirmation. Theor Comput Sci 384(1):33–48

    MathSciNet  CrossRef  MATH  Google Scholar 

  • Hutter M (2012) One decade of universal artificial intelligence. In: Wang P, Goertzel B (eds) Theoretical Foundations of Artificial General Intelligence. Atlantis Press, Amsterdam, pp 67–88

    CrossRef  Google Scholar 

  • Lattimore T, Hutter M (2011) No free lunch versus Occam’s razor in supervised learning. In: Proceedings of the Solomonoff 85th memorial conference, Melbourne. Volume 7070 of LNAI. Springer, pp 223–235

    Google Scholar 

  • Li M, Vitányi PMB (2008) An Introduction to Kolmogorov Complexity and Its Applications, 3rd edn. Springer, Berlin

    CrossRef  MATH  Google Scholar 

  • Orseau L, Lattimore T, Hutter M (2013) Universal knowledge-seeking agents for stochastic environments. In: Proceedings of the 24th international conference on algorithmic learning theory (ALT’13), Singapore. Volume 8139 of LNAI. Springer, pp 158–172

    Google Scholar 

  • Rathmanner S, Hutter M (2011) A philosophical treatise of universal induction. Entropy 13(6):1076–1136

    MathSciNet  CrossRef  MATH  Google Scholar 

  • Schmidhuber J (2002) Hierarchies of generalized Kolmogorov complexities and nonenumerable universal measures computable in the limit. Int J Found Comput Sci 13(4):587–612

    MathSciNet  CrossRef  MATH  Google Scholar 

  • Solomonoff RJ (1964) A formal theory of inductive inference: Parts 1 and 2. Inf Control 7:1–22 and 224–254

    Google Scholar 

  • Solomonoff RJ (1978) Complexity-based induction systems: comparisons and convergence theorems. IEEE Trans Inf Theory IT-24:422–432

    MathSciNet  CrossRef  MATH  Google Scholar 

  • Veness J, Ng KS, Hutter M, Uther W, Silver D (2011) A Monte-Carlo AIXI approximation. J Artif Intell Res 40:95–142

    MathSciNet  MATH  Google Scholar 

  • Wood I, Sunehag P, Hutter M (2011) (Non-)equivalence of universal priors. In: Proceedings of the Solomonoff 85th memorial conference, Melbourne. Volume 7070 of LNAI. Springer, pp 417–425

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Marcus Hutter .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and Permissions

Copyright information

© 2017 Springer Science+Business Media New York

About this entry

Cite this entry

Hutter, M. (2017). Universal Learning Theory. In: Sammut, C., Webb, G.I. (eds) Encyclopedia of Machine Learning and Data Mining. Springer, Boston, MA. https://doi.org/10.1007/978-1-4899-7687-1_867

Download citation