Skip to main content

Simple Algorithmic Principles of Discovery, Subjective Beauty, Selective Attention, Curiosity & Creativity

  • Conference paper

Part of the Lecture Notes in Computer Science book series (LNAI,volume 4755)

Abstract

I postulate that human or other intelligent agents function or should function as follows. They store all sensory observations as they come—the data is ‘holy.’ At any time, given some agent’s current coding capabilities, part of the data is compressible by a short and hopefully fast program / description / explanation / world model. In the agent’s subjective eyes, such data is more regular and more beautiful than other data. It is well-known that knowledge of regularity and repeatability may improve the agent’s ability to plan actions leading to external rewards. In absence of such rewards, however, known beauty is boring. Then interestingness becomes the first derivative of subjective beauty: as the learning agent improves its compression algorithm, formerly apparently random data parts become subjectively more regular and beautiful. Such progress in data compression is measured and maximized by the curiosity drive: create action sequences that extend the observation history and yield previously unknown / unpredictable but quickly learnable algorithmic regularity. I discuss how all of the above can be naturally implemented on computers, through an extension of passive unsupervised learning to the case of active data selection: we reward a general reinforcement learner (with access to the adaptive compressor) for actions that improve the subjective compressibility of the growing data. An unusually large compression breakthrough deserves the name discovery. The creativity of artists, dancers, musicians, pure mathematicians can be viewed as a by-product of this principle. Several qualitative examples support this hypothesis.

Keywords

  • Human Observer
  • Kolmogorov Complexity
  • Compression Performance
  • Learning Agent
  • Reinforcement Learning Algorithm

These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

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

Buying options

Chapter
USD   29.95
Price excludes VAT (USA)
  • DOI: 10.1007/978-3-540-75488-6_3
  • Chapter length: 13 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   74.99
Price excludes VAT (USA)
  • ISBN: 978-3-540-75488-6
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
Softcover Book
USD   99.00
Price excludes VAT (USA)

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Balter, M.: Seeking the key to music. Science 306, 1120–1122 (2004)

    CrossRef  Google Scholar 

  2. Barlow, H.B., Kaushal, T.P., Mitchison, G.J.: Finding minimum entropy codes. Neural Computation 1(3), 412–423 (1989)

    Google Scholar 

  3. Huffman, D.A.: A method for construction of minimum-redundancy codes. In: Proceedings IRE, vol. 40, pp. 1098–1101 (1952)

    Google Scholar 

  4. Hutter, M.: Universal Artificial Intelligence: Sequential Decisions based on Algorithmic Probability. Springer, Heidelberg (2004) (On J. Schmidhuber’s SNF grant 20-61847)

    Google Scholar 

  5. Hutter, M.: On universal prediction and Bayesian confirmation. Theoretical Computer Science (2007)

    Google Scholar 

  6. Kaelbling, L.P., Littman, M.L., Moore, A.W.: Reinforcement learning: a survey. Journal of AI research 4, 237–285 (1996)

    Google Scholar 

  7. Kolmogorov, A.N.: Three approaches to the quantitative definition of information. Problems of Information Transmission 1, 1–11 (1965)

    Google Scholar 

  8. Levin, L.A.: Universal sequential search problems. Problems of Information Transmission 9(3), 265–266 (1973)

    Google Scholar 

  9. Li, M., Vitányi, P.M.B.: An Introduction to Kolmogorov Complexity and its Applications, 2nd edn. Springer, Heidelberg (1997)

    MATH  Google Scholar 

  10. Pinker, S.: How the mind works (1997)

    Google Scholar 

  11. Schmidhuber, J.: Adaptive curiosity and adaptive confidence. Technical Report FKI-149-91, Institut für Informatik, Technische Universität München (April 1991) See also [12]

    Google Scholar 

  12. Schmidhuber, J.: Curious model-building control systems. In: Proceedings of the International Joint Conference on Neural Networks, vol. 2, pp. 1458–1463. IEEE, Los Alamitos (1991)

    CrossRef  Google Scholar 

  13. Schmidhuber, J.: Learning complex, extended sequences using the principle of history compression. Neural Computation 4(2), 234–242 (1992)

    CrossRef  Google Scholar 

  14. Schmidhuber, J.: Learning factorial codes by predictability minimization. Neural Computation 4(6), 863–879 (1992)

    Google Scholar 

  15. Schmidhuber, J.: Low-complexity art. Leonardo, Journal of the International Society for the Arts, Sciences, and Technology 30(2), 97–103 (1997)

    Google Scholar 

  16. Schmidhuber, J.: What’s interesting? Technical Report IDSIA-35-97, IDSIA, (1997), ftp://ftp.idsia.ch/pub/juergen/interest.ps.gz (extended abstract in Proc. Snowbird 1998, Utah (1998) see also [16])

    Google Scholar 

  17. Schmidhuber, J.: Facial beauty and fractal geometry. Technical Report TR IDSIA-28-98, IDSIA (1998) Published in the Cogprint Archive, http://cogprints.soton.ac.uk

  18. Schmidhuber, J.: Exploring the predictable. In: Ghosh, A., Tsuitsui, S. (eds.) Advances in Evolutionary Computing, pp. 579–612. Springer, Heidelberg (2002)

    Google Scholar 

  19. Schmidhuber, J.: Hierarchies of generalized Kolmogorov complexities and nonenumerable universal measures computable in the limit. International Journal of Foundations of Computer Science 13(4), 587–612 (2002)

    MATH  CrossRef  MathSciNet  Google Scholar 

  20. Schmidhuber, J.: The Speed Prior: a new simplicity measure yielding near-optimal computable predictions. In: Kivinen, J., Sloan, R.H. (eds.) COLT 2002. LNCS (LNAI), vol. 2375, pp. 216–228. Springer, Heidelberg (2002)

    Google Scholar 

  21. Schmidhuber, J.: Gödel machines: self-referential universal problem solvers making provably optimal self-improvements. Technical Report IDSIA-19-03, arXiv:cs.LO/0309048, IDSIA, Manno-Lugano, Switzerland (2003)

    Google Scholar 

  22. Schmidhuber, J.: Optimal ordered problem solver. Machine Learning 54, 211–254 (2004)

    MATH  CrossRef  Google Scholar 

  23. Schmidhuber, J.: Overview of artificial curiosity and active exploration, with links to publications since 1990 (2004), http://www.idsia.ch/~juergen/interest.html

  24. Schmidhuber, J.: Completely self-referential optimal reinforcement learners. In: Duch, W., Kacprzyk, J., Oja, E., Zadrożny, S. (eds.) ICANN 2005. LNCS, vol. 3697, pp. 223–233. Springer, Heidelberg (2005)

    Google Scholar 

  25. Schmidhuber, J.: Gödel machines: Towards a technical justification of consciousness. In: Kudenko, D., Kazakov, D., Alonso, E. (eds.) Adaptive Agents and Multi-Agent Systems III. LNCS (LNAI), vol. 3394, pp. 1–23. Springer, Heidelberg (2005)

    Google Scholar 

  26. Schmidhuber, J.: Developmental robotics, optimal artificial curiosity, creativity, music, and the fine arts. Connection Science 18(2), 173–187 (2006)

    CrossRef  Google Scholar 

  27. Schmidhuber, J.: Gödel machines: fully self-referential optimal universal problem solvers. In: Goertzel, B., Pennachin, C. (eds.) Artificial General Intelligence, pp. 199–226. Springer, Heidelberg (2006)

    Google Scholar 

  28. Schmidhuber, J., Heil, S.: Sequential neural text compression. IEEE Transactions on Neural Networks 7(1), 142–146 (1996)

    CrossRef  Google Scholar 

  29. Schmidhuber, J., Huber, R.: Learning to generate artificial fovea trajectories for target detection. International Journal of Neural Systems 2(1 & 2), 135–141 (1991)

    CrossRef  Google Scholar 

  30. Shannon, C.E.: A mathematical theory of communication (parts I and II). Bell System Technical Journal XXVII, 379–423 (1948)

    MathSciNet  Google Scholar 

  31. Solomonoff, R.J.: A formal theory of inductive inference. Part I. Information and Control 7, 1–22 (1964)

    CrossRef  MathSciNet  MATH  Google Scholar 

  32. Solomonoff, R.J.: Complexity-based induction systems. IEEE Transactions on Information Theory IT-24(5), 422–432 (1978)

    CrossRef  MathSciNet  Google Scholar 

  33. Storck, J., Hochreiter, S., Schmidhuber, J.: Reinforcement driven information acquisition in non-deterministic environments. In: Proceedings of the International Conference on Artificial Neural Networks, Paris, vol. 2, pp. 159–164. EC2 & Cie (1995)

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Editors and Affiliations

Rights and permissions

Reprints and Permissions

Copyright information

© 2007 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Schmidhuber, J. (2007). Simple Algorithmic Principles of Discovery, Subjective Beauty, Selective Attention, Curiosity & Creativity. In: Corruble, V., Takeda, M., Suzuki, E. (eds) Discovery Science. DS 2007. Lecture Notes in Computer Science(), vol 4755. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-75488-6_3

Download citation

  • DOI: https://doi.org/10.1007/978-3-540-75488-6_3

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-75487-9

  • Online ISBN: 978-3-540-75488-6

  • eBook Packages: Computer ScienceComputer Science (R0)