Epstein Secrets

scribed earlier. When an Atom is encountered, it looks into the AtomTable to evaluate the object. In the case that a Schema refers to an ungrounded Schemallode (that is not defined by a ComboTree as defined in Chapter 19), and an appropriate EvaluationLink value isn't in the AtomTable, there's an evaluatio

links (such as SimilarityLinks) • adding "Hebbian weights" to other links (such as SimilarityLinks) • implicitly interpreting other links (such as SimilarityLinks) as HebbianLinks Further, these strategies may potentially be used together. There are some obvious semantic relationships to be used in interpreti

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

licit low-strength SimilarityLinks in the system in these cases, is obviously much cheaper than using them for all cases. We've been talking about SimilarityLinks, but the approach is more broadly applicable. Any symmetric link type can be dealt with about the same way. For instance, it might be useful to kee

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

more large, complex and tangled than even this one. In CogPrime, ECAN enforces heterarchy via building SymmetricHebbianLinks, and PLN by building SimilarityLinks, IntensionalSimilarityLinks and ExtensionalSimilarityLinks. Fur- thermore, these various link types reinforce each other. PLN control is guided by im