Transactions of the Institute of Systems, Control and Information Engineers
Online ISSN : 2185-811X
Print ISSN : 1342-5668
ISSN-L : 1342-5668
Connectionist Learning with High-order Functional Networks and Analyses of Its Interval Representation
Akira NAMATAME
Author information
JOURNALS FREE ACCESS

1990 Volume 3 Issue 11 Pages 372-380

Details
Abstract

We show the Inductive capability or generality of a connectionist learning depends on the network architecture. It is shown that the conventional network architecture is inadequate for representing and learning complex nonlinear structure of the continuous mapping. We propose a new network architecture, high-order functional networks, with some nonmonotonic functional units as input units. It is shown that a high-order functional network trained with backpropagation can generalize and infer the nonlinear structure between the continuous variables. Nonlinear mappings are characterized by the positions and the number of their extreme points and the curvatures at the extreme points. It is shown that the combination of the, high-order functional input units and the sigmoid-type hidden units make it possible to realize and acquire a proper internal representation of the network and that extracts those features of the task domain.

Information related to the author
© The Institute of Systems, Control and Information Engineers
Previous article Next article
feedback
Top