Epstein Secrets

hich data and procedure are explicitly identical, and there is just one new active data structure in place of the distinction between AtomSpace and MindAgents Where on this continuum does the "mere learning" end and the "real self-modification" start? In this chapter we consider some mechanisms for "adva

ilation 319 schema learning the learning of schemata carrying out cognitive processes in more specialized, context-dependent ways than the general MindAgents do. Eventually, once a CogPrime instance becomes sufficiently complex and advanced, these cognitive schema may replace the MindAgents altogether, l

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

mpilation 319 schema learning the learning of schemata carrying out cognitive processes in more specialized, context-dependent ways than the general MindAgents do. Eventually, once a CogPrime instance becomes sufficiently complex and advanced, these cognitive schema may replace the MindAgents altogether, lea

which data and procedure are explicitly identical, and there is just one new active data structure in place of the distinction between AtomSpace and MindAgents Where on this continuum does the "mere learning" end and the "real self-modification" start? In this chapter we consider some mechanisms for "advan

ar 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

idual cognitive processes. The CogPrime design gravitates more toward the latter approach. though also with some specific mechanisms within various MindAgents; and efforts have been made to have these specific mechanisms modulated by the generic attention allocation structures and dynamics wherever possibl

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

links that could simply be found by the pattern matcher when trying to find variable assignments to satisfy (El, E2, E3, E4}. 36.4.1 Breakdown into MindAgents To make this sort of PLN dynamic work, we require a number of MindAgents to be operating "ambiently" in the background whenever inference is occurr

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

sambigua- tion that needs to be done to get the structure of the resultant Atom-set correct. Any further disambiguation is left to be done later, by MindAgents acting on the Atom-sets after they've already been placed in the AtomSpace. • In the old approach, the RelEx2Frame rules attempted, in many cases,

ch one denoting a "sense" of the word. The clusters are defined by the following relationships: 1. ConceptNodes within a cluster have high-strength SimilarityLinks to each other 2. ConceptNodes in different clusters have low-strength (i.e. dissimilarity-denoting) Similar- ityLinks to each other When a word is