Probabilistic Growth and Mining of Combinations: A Unifying Meta-Algorithm for Practical General Intelligence
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).
- 3.Goertzel, B.: A system-theoretic analysis of focused cognition, and its implications for the emergence of self and attention. Dynamical Psychology (2006)Google Scholar
- 4.Goertzel, B.: Toward a formal definition of real-world general intelligence. In: Proceedings of AGI 2010 (2010)Google Scholar
- 5.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)Google Scholar
- 6.Goertzel, B., Pennachin, C., Geisweiller, N.: Engineering General Intelligence, Part 2: The CogPrime Architecture for Integrative, Embodied AGI. Atlantis Thinking Machines. Springer, Heidelberg (2013)Google Scholar
- 7.Looks, M.: Competent Program Evolution. Ph.D. Thesis, Computer Science Department, Washington University (2006)Google Scholar
- 10.Weinbaum, D.W., Veitas, V.: Open-ended intelligence (2015). http://arXiv.org/abs/1505.06366