Let us now return to the problem of how a STRAM is to maintain its approximate network-of-emergence structure. One way to approach this optimization problem is via the multilevelmethodology (Goertzel, 1989). This application of the multilevel methodology bears a strongsimilarity to Achi Brandt’s (1985) multilevel algorithm for the Ising spin problem. The first level…
It is rather difficult to study the structure of human long-term memory, since we cannot lookinto a person’s brain or mind to determine the processes by which their memory organizes itself.The only aspect of memory which is open to study is memory access. In particular, a great dealof attention has been devoted to the…
It is clear that analogy cannot work effectively without recourse to an effective method ofstoring patterns. However, I suggest that an even stronger statement holds: the nature of analogyactually dictates a particular type of memory structure. The only way analogy can workeffectively is if it is coupled with a memory that is specifically structured…
The neurons of the cortex are organized in clusters, each containing 50 to 10,000 neurons. Theneurons of each cluster are connected primarily to other neurons in the same cluster. Edelman(1988) has proposed that it makes sense to think of connections between clusters, not justindividual neurons, as being reinforced or inhibited; and he has backed…
We have not yet discussed the possibility that analogies might be justified by analogy.Obviously, analogy as a general mode of thought cannot be justified by analogy; that would becircular reasoning. But, just as particular analogies can be justified by inductive or deductivebackground knowledge, so can particular analogies be justified by analogical backgroundknowledge. In some…
Induction and analogy are obviously closely related. In induction one assumes the future willbe similar to the past, and tries to guess which of a set of past patterns will continue into thefuture. In analogy one assumes that similar entities will have similar patterns, and directs patternrecognition on this basis. The difference is that…
Analogy is far more powerful than transitive reasoning; nonetheless, according to the presentanalysis it is nothing more than a subtler way of manipulating the pattern distance. I willintroduce three forms of analogical reasoning — structural analogy, modeling, and contextualanalogy — and propose a unified structure for analogical reasoning which encompasses all ofthem. It is…
Induction, as we have analyzed it, requires a store of patterns on which to operate. We havenot said how these patterns are to be obtained. Any general global optimization algorithm couldbe applied to the problem of recognizing patterns in an environment. But pattern recognition is adifficult problem, and a mind needs rapid, reasonably accurate…
We have discussed several different measures of static complexity, which measure ratherdifferent things. But all these measures have one thing in common: they work by singling out theone pattern which minimizes some quantity. It is equally interesting to study the total amount of structure in an entity. For instance, suppose x and x% both…
Koppel [8] has recently proposed an alternative to the KCS complexity measure. According toKoppel’s measure, the sequences which are most complex are not the structureless ones. Neither,of course, are they the ones with very simple structures, like 00000000000…. Rather, the morecomplex sequences are the ones with more "sophisticated" structures.The basic idea [10] is that…