A novel class of neural networks with quadratic junctions

Nicholas DeClaris, Mu chun Su

Research output: Contribution to journalConference articlepeer-review

13 Scopus citations


The authors discuss the architecture and training properties of a multilayer feedforward neural network class that uses quadratic junctions in a neural architecture that uses effectively the backpropagation learning algorithm given by P. J. Werbos (1989). Both the architecture of the quadratic junctions and the backpropagation were adopted so as to endow the networks with appealing training properties (under supervision) and acceptable generalizations. Complexity and learning aspects of this class are examined and compared with traditional networks that use linear junctions.

Original languageEnglish
Pages (from-to)1557-1562
Number of pages6
JournalProceedings of the IEEE International Conference on Systems, Man and Cybernetics
StatePublished - 1991
EventConference Proceedings of the 1991 IEEE International Conference on Systems, Man, and Cybernetics - Charlottesville, VA, USA
Duration: 13 Oct 199116 Oct 1991


Dive into the research topics of 'A novel class of neural networks with quadratic junctions'. Together they form a unique fingerprint.

Cite this