Jw. Wang, PRINCIPAL INTERCONNECTIONS IN HIGHER-ORDER HEBBIAN-TYPE ASSOCIATIVE, IEEE transactions on knowledge and data engineering, 10(2), 1998, pp. 342-345
Citations number
8
Categorie Soggetti
Computer Science Artificial Intelligence","Computer Science Information Systems","Engineering, Eletrical & Electronic","Computer Science Artificial Intelligence","Computer Science Information Systems
The existence of principal interconnections useful in solving the prol
iferation problem in higher order Hebbian-type associative memories is
introduced. Among all legal interconnections, we prove there exists a
subset T-pr that carries more information than the others. Regardless
of the network order p, the elements in T-pr are shown to be those in
terconnections T that fall within the range of root m(s) less than or
equal to \T\ less than or equal to 2 root m(s), where m(s) equals the
number of stored codewords. Memories that use only T-pr can maintain o
riginal generalization performance, using less than 50 percent of the
total number of interconnections.