Epstein Secrets

ges 51 Our goal in this chapter Ls to provide practical techniques for approximating the ideal pro- vided by algorithmic probability, based on what Pei Wang has termed the assumption of in- sufficient knowledge and resources tWan061, and assuming an AGI architecture that's at least vaguely humanlike in n

latter situation is disallowed on the software level, and is assumed in discussions not to occur. Sonic Atoms have natural names. For instance. the Schemallode corresponding to the ele- mentary schema function + may quite naturally be named "+". The NumberNode corresponding to the number .5 may naturally be

hat ExecutionLink X A B ExecutionLink2 A B means: X so that ExecutionLink A X B ExecutionLink3 A B means: X so that ExecutionLink A B X Finally, a Schemallode may be associated with a structure called a Graph. Where S is a Schemallode, Graph(S) (x,y): ExecutionLink S x y ) Sometimes, the graph of a Sche

y different yet both appear cognitively necessary. The argument for using probability in an AGI system is assailed by some AGI researchers such as Pei Wang, but we are swayed by the theoretical arguments in favor of probability theory's mathematically fundamental nature, as well as the massive demonstra

by the quest of figuring out which procedures can be expected to achieve a certain goal in a certain sort of context. • Grounded Schemallode: See Schemallode, Grounded. • Hebbian Learning: An aspect of Attention Allocation, centered on creating and updating HebbianLinks, which represent the simultaneous

achines. Oxford University Press, 2010. Wan95. P. Wang. Non-Axiomatic Reasoning System. PhD Thesis, Indiana University. Bloomington, 1995. Wan06. Pei Wang. Rigid Flexibility: The Logic of Intelligence. Springer. 2006. Was09. Mark Weser. Ethics for self-improving machines. In ACf-09, 2009. http://vimeo

plementation, the system can still reason about its use of different mind dynamics by considering each MindAgent as a virtual Procedure with a real Schemallode attached to it. This can lead to some valuable learning, with the obvious limitation that in this approach the system is thinking about its MindAgen