Epstein Secrets

its own hardware and software infrastructure. CogPrime represents procedures as programs in an internal programming language called "Combo." While Combo has a textual representation, described online at the OpenCog wiki, this isn't one of its more important aspects (and may be redesigned slightly or

an internal node of a program, can also live in its own Atom. For example. a number in a program tree corresponds to a NmnberNode; an argument in a Combo program already corresponds to some Atom; and an operator in a program can be wrapped up in a Schemallode all its own, and considered as a one-leaf

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

r the latter are learned via MOSES or via some other means. The textual realization of Combo resembles LISP with less syntactic sugar. Internally a Combo program is represented as a program tree. • Composer: In the PLN design, a rule is denoted a composer if it needs premises for generating its conse

ve its fingers to pick up a cup, coordinating its movements with its visual perceptions. It's certainly possible to represent this sort of thing in Combo, but Combo may be an awkward tool. However, if one represents low-level procedures like this using another method, e.g. learned cell assemblies in a

the question of programs in what programming language, and in this context we have made a fairly traditional choice, using a special language called Combo that is essentially a minor variant of LISP, and supplying Combo with a set of customized primitives intended to reduce the length of the typical p

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

uesses produced by pure procedure learning methods), it may still be valuable to have this procedure in compact and rapidly executable form such as Combo provides. To proceed with the technical description of predicate schematization in CogPrime. we first need the notion of an "executable predicate".

tand: all else equal, a predicate embodied in a small Combo tree is better than a predicate embodied in a big one. There is some work hidden here in Combo tree reduction; ideally, one would like to find the smallest representation of a given Combo tree, but this is a computationally formidable problem

On the other hand, given a ConceptNode C involved in inferred ExecutionLinks of the form ExecutionLink C Ai Bi i-1, .. ,n one may wish to find a Schemallode so that the corresponding Schemallode will fulfill this same set of ExecutionLinks. It may seem surprising at first that a ConceptNode might be inv

r the latter are learned via MOSES or via some other means. The textual realization of Combo resembles LISP with less syntactic sugar. Internally a Combo program is represented as a program tree. • Composer: In the PLN design, a rule is denoted a composer if it needs premises for generating its conse

p the rules might profitably be ported into the Atomspace as ImplicationLinks. • Representation Building: A stage within MOSES, wherein a candidate Combo program tree (within a deme) is modified by replacing one or more tree nodes with alternative tree nodes, thus obtaining a new, different candidate

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