Skip to main content
Springer Nature Link
Log in

Bridging AGI Theory and Practice with Galois Connections

  • Conference paper
  • First Online:
Artificial General Intelligence (AGI 2023)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 13921))

Included in the following conference series:

Abstract

Multiple cognitive algorithms posited to play a key role in AGI (forward and backward chaining inference, clustering and concept formation, evolutionary and reinforcement learning, probabilistic programming, etc.) are given a common formulation as recursive discrete decision processes involving optimizing functions defined over metagraphs, in which the key decisions involve sampling from probability distributions over metagraphs and enacting sets of combinatory operations on selected sub-metagraphs. This forms a bridge between abstract conceptions of general intelligence founded on notions of algorithmic information and complex systems theory, and the practical design of multi-paradigm AGI systems.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Franz, A., Gogulya, V., Löffler, M.: WILLIAM: a monolithic approach to AGI. In: Hammer, P., Agrawal, P., Goertzel, B., Iklé, M. (eds.) AGI 2019. LNCS (LNAI), vol. 11654, pp. 44–58. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-27005-6_5

    Chapter  Google Scholar 

  2. Gibbons, J.: An initial-algebra approach to directed acyclic graphs. In: Möller, B. (ed.) MPC 1995. LNCS, vol. 947, pp. 282–303. Springer, Heidelberg (1994). https://doi.org/10.1007/3-540-60117-1_16

    Chapter  Google Scholar 

  3. Goertzel, B.: Folding and unfolding on metagraphs (2020). https://arxiv.org/abs/2012.01759

  4. Goertzel, B.: Grounding Occam’s razor in a formal theory of simplicity. arXiv preprint arXiv:2004.05269 (2020)

  5. Goertzel, B.: Paraconsistent foundations for probabilistic reasoning, programming and concept formation. arXiv preprint arXiv:2012.14474 (2020)

  6. Goertzel, B.: Patterns of cognition: cognitive algorithms as Galois connections fulfilled by chronomorphisms on probabilistically typed metagraphs. arXiv preprint arXiv:2102.10581 (2021)

  7. Goertzel, B.: Toward a general theory of general intelligence: a patternist perspective. arXiv preprint arXiv:2103.15100 (2021)

  8. Goertzel, B., Pennachin, C.: How might probabilistic reasoning emerge from the brain? In: Proceedings of the First AGI Conference, vol. 171, p. 149. IOS Press (2008)

    Google Scholar 

  9. Goertzel, B., Pennachin, C., Geisweiller, N.: Engineering General Intelligence, Part 1: A Path to Advanced AGI via Embodied Learning and Cognitive Synergy. Atlantis Thinking Machines, Springer, Heidelberg (2013). https://doi.org/10.2991/978-94-6239-027-0

    Book  Google Scholar 

  10. Hutter, M.: Universal Artificial Intelligence: Sequential Decisions Based on Algorithmic Probability. Springer, Heidelberg (2005). https://doi.org/10.1007/b138233

    Book  MATH  Google Scholar 

  11. van de Meent, J.W., Paige, B., Yang, H., Wood, F.: An introduction to probabilistic programming. arXiv preprint arXiv:1809.10756 (2018)

  12. Mu, S.C., Oliveira, J.N.: Programming from Galois connections. J. Log. Algebraic Program. 81(6), 680–704 (2012)

    Article  MathSciNet  MATH  Google Scholar 

  13. Schmidhuber, J.: Godel machines: fully self-referential optimal universal self-improvers. In: Goertzel, B., Pennachin, C. (eds.) Artificial General Intelligence. COGTECH, pp. 119–226. Springer, Heidelberg (2006). https://doi.org/10.1007/978-3-540-68677-4_7

    Chapter  Google Scholar 

  14. Schmidhuber, J.: Optimal ordered problem solver. Mach. Learn. 54(3), 211–254 (2004). https://doi.org/10.1023/B:MACH.0000015880.99707.b2

    Article  MATH  Google Scholar 

  15. Torczon, V.: Pattern search methods for nonlinear optimization. In: SIAG/OPT Views and News. Citeseer (1995)

    Google Scholar 

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

    Article  MathSciNet  MATH  Google Scholar 

  17. Weinbaum, D., Veitas, V.: Open ended intelligence: the individuation of intelligent agents. J. Exp. Theor. Artif. Intell. 29(2), 371–396 (2017)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. OpenCog Foundation, Rockville, USA

    Ben Goertzel

  2. SingularityNET Foundation, Amsterdam, The Netherlands

    Ben Goertzel

Authors
  1. Ben Goertzel
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Ben Goertzel .

Editor information

Editors and Affiliations

  1. Department of Psychology, Stockholm University, Stockholm, Sweden

    Patrick Hammer

  2. Örebro University, Örebro, Sweden

    Marjan Alirezaie

  3. University of Gothenburg, Gothenburg, Sweden

    Claes Strannegård

Rights and permissions

Reprints and permissions

Copyright information

© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Goertzel, B. (2023). Bridging AGI Theory and Practice with Galois Connections. In: Hammer, P., Alirezaie, M., Strannegård, C. (eds) Artificial General Intelligence. AGI 2023. Lecture Notes in Computer Science(), vol 13921. Springer, Cham. https://doi.org/10.1007/978-3-031-33469-6_12

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-33469-6_12

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-33468-9

  • Online ISBN: 978-3-031-33469-6

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics