SingularityNET: General Theory of General Intelligence: Universal AI Algorithms (5/10)
This is Episode 5 in a series of videos discussing the General Theory of General Intelligence as overviewed in the paper Goertzel, Ben. “The General Theory of General Intelligence: A Pragmatic Patternist Perspective.”
This episode reviews some theoretical work regarding algorithms and processes that in some senses realize or manifest “optimal or near optimal general intelligence” — even if they are not practical to implement. These ideas provide some inspiration and framework for developing practical AGI systems.
Some additional references relevant to this episode are:
Hutter, Marcus (2005). Universal Artificial Intelligence. Sequential Decisions based on Algorithmic Probability. Springer
Joel Veness et al (2010). A Monte Carlo AIXI Approximation.
Franz, Arthur (2015). Toward Tractable Universal Induction Through Recursive Program Learning, in Proceedings of AGI-5 Springer
Franz, Arthur (2019). WILLIAM: A Monolithic Approach to AGI, in Proceedings of AGI-19, Springer Artificial General Intelligence (pp.44-58)
Schmidhuber, Jürgen. “Gödel machines: Fully self-referential optimal universal self-improvers.” In Artificial general intelligence, pp. 199-226. Springer, Berlin, Heidelberg, 2007.
Steunebrink, Bas R., and Jürgen Schmidhuber. “A family of Gödel machine implementations.” In International Conference on Artificial General Intelligence, pp. 275-280. Springer, Berlin, Heidelberg, 2011.
Steunebrink, Bas R., and JÃ¼rgen Schmidhuber. “Towards an actual gödel machine implementation: A lesson in self-reflective systems.” In Theoretical Foundations of Artificial General Intelligence, pp. 173-195. Atlantis Press, Paris, 2012.
SingularityNET is a decentralized marketplace for artificial intelligence. We aim to create the world’s global brain with a full-stack AI solution powered by a decentralized protocol.
We gathered the leading minds in machine learning and blockchain to democratize access to AI technology. Now anyone can take advantage of a global network of AI algorithms, services, and agents.