Abstract
A new conceptual framing of the notion of the general intelligence is outlined, in the form of a universal learning meta-algorithm called Probabilistic Growth and Mining of Combinations (PGMC). Incorporating ideas from logical inference systems, Solomonoff induction and probabilistic programming, PGMC is a probabilistic inference based framework which reflects processes broadly occurring in the natural world, is theoretically capable of arbitrarily powerful generally intelligent reasoning, and encompasses a variety of existing practical AI algorithms as special cases. Several ways of manifesting PGMC using the OpenCog AI framework are described. It is proposed that PGMC can be viewed as a core learning process serving as the central dynamic of real-world general intelligence; but that to achieve high levels of general intelligence using limited computational resources, it may be necessary for cognitive systems to incorporate multiple distinct structures and dynamics, each of which realizes this core PGMC process in a different way (optimized for some particular sort of sub-problem).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
- 2.
See [10] for a deep discussion of how general intelligence transcends goal-pursuit.
- 3.
Or see http://wiki.opencog.org/w/CogPrime_Overview for an informal online overview.
- 4.
See http://wiki.opencog.org/wikihome/index.php/OpenCoggy_Probabilistic_Programming for more details.
- 5.
E.g. the easiest way to do this in terms of OpenCog’s current assemblage of Atom types, is simply to consider polymorphic, higher-order-functional SchemaNodes – i.e. SchemaNodes whose inputs may be SchemaNodes and whose outputs may be SchemaNodes.
- 6.
- 7.
Discussed in more depth at http://wiki.opencog.org/wikihome/index.php/OpenCoggy_Probabilistic_Programming).
- 8.
See http://wiki.opencog.org/wikihome/index.php/Agglomerative_Clustering_in_Atomspace_using_the_URE on the OpenCog wiki site for specifics.
- 9.
References
Potapov, A., Batishcheva, V., Rodionov, S.: Optimization framework with minimum description length principle for probabilistic programming. In: Bieger, J., Goertzel, B., Potapov, A. (eds.) AGI 2015. LNCS, vol. 9205, pp. 331–340. Springer, Heidelberg (2015)
Goertzel, B.: Chaotic Logic. Plenum, New York (1994)
Goertzel, B.: A system-theoretic analysis of focused cognition, and its implications for the emergence of self and attention. Dynamical Psychology (2006)
Goertzel, B.: Toward a formal definition of real-world general intelligence. In: Proceedings of AGI 2010 (2010)
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)
Goertzel, B., Pennachin, C., Geisweiller, N.: Engineering General Intelligence, Part 2: The CogPrime Architecture for Integrative, Embodied AGI. Atlantis Thinking Machines. Springer, Heidelberg (2013)
Looks, M.: Competent Program Evolution. Ph.D. Thesis, Computer Science Department, Washington University (2006)
Solomonoff, R.: A formal theory of inductive inference part I. Inf. Control 7(1), 1–22 (1964)
Solomonoff, R.: A formal theory of inductive inference part II. Inf. Control 7(2), 224–254 (1964)
Weinbaum, D.W., Veitas, V.: Open-ended intelligence (2015). http://arXiv.org/abs/1505.06366
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this paper
Cite this paper
Goertzel, B. (2016). Probabilistic Growth and Mining of Combinations: A Unifying Meta-Algorithm for Practical General Intelligence. In: Steunebrink, B., Wang, P., Goertzel, B. (eds) Artificial General Intelligence. AGI 2016. Lecture Notes in Computer Science(), vol 9782. Springer, Cham. https://doi.org/10.1007/978-3-319-41649-6_35
Download citation
DOI: https://doi.org/10.1007/978-3-319-41649-6_35
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-41648-9
Online ISBN: 978-3-319-41649-6
eBook Packages: Computer ScienceComputer Science (R0)