Each level in the Asa H hierarchical memory is composed out of concepts each one of which consists of features defined on the next lower level in the hierarchy. (The concepts can be thought of as vectors and the features are the vector's components.)
In our publications on Asa H we have described ways in which we may prune some of these features. Standard statistical measures of independence can also be used to prune features; mutual information measures, Fisher's discrimination index, the chi-square test of independence, etc.
No comments:
Post a Comment