摘要 |
<p>A single layer parallel distributed processing network (10) is characterized by having connection weights between nodes that are defined by an [N x N] information storage matrix (A) that satisfies the matrix equation: [A] [T] = [T] [Μ], where [Μ] is an [N x N] diagonal matrix the components of which are the eigenvalues of the matrix [A] and [T] is an [N x N] similarity transformation matrix whose columns are formed of some predetermined number M of target vectors (where M <= N) and whose remaining columns are formed of some predetermined number Q of slack vectors (where Q = N - M), both of which together comprise the eigenvectors of [A].</p> |