REFERENCES
REFERENCES
It is true that our definition is very similar to that proposed by Hawkins (reference 5). Compare for example his definition of learning machines (page 31 of reference 5). But the subsequent developments reviewed therein are different from the one we have followed.
We make the latter statement despite the fact that we employ a statistical treatment of self-organization. We may predict the performance of, for example, the NPO by using a statistical description, but it does not necessarily follow that the NPO computes statistics.
The spaces W, X, Y, and Z are stochastic spaces; that is, each space is defined as the ordered pair (X,p(X)) wherep(X) = {p(x) ∋ x ∈ X}, p(x) ≥ 0, x ∈ X and ∫x p(x)dx = 1. Such spaces possess a metrizable topology.
We use the following convention for probability distributions: if the arguments of p( ) are different, they are different functions, thus:p(x) ≠ p(y)even ify = x.
One can prove the existence of a metric directly but in order to perform the metrization the space has to be decomposed first. But decomposing a space without having a metric calls for a neat trick, accomplished (as far as we know) only by the method used by the SOM.
In this example we use a hemisphere; in general, it would be a spherical cap.