Share Email Print

Proceedings Paper

Classifier neural net with complex-valued weights and square-law nonlinearities
Author(s): David P. Casasent; Sanjan Natarajan
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

A new pattern recognition classifier neural net (NN) is described that uses complex-valued weights and square-law nonlinearities. We show that these weights and nonlinearities inherently produce higher-order decision surfaces and thus we expect better classification performance (PC). We refer to this as the piecewise hyperquadratic neural net (PQNN) since each hidden layer neuron inherently provides a hyperquadratic decision surface and the combination of neurons provides piecewise hyperquadratic decision surfaces. We detail the learning algorithm for this PQNN and provide initial results on synthetic data showing its advantages over the backpropagation and other NNs. We also note a new technique to provide improved classification results when there are significantly different numbers of samples per class.

Paper Details

Date Published: 20 August 1993
PDF: 11 pages
Proc. SPIE 2055, Intelligent Robots and Computer Vision XII: Algorithms and Techniques, (20 August 1993); doi: 10.1117/12.150175
Show Author Affiliations
David P. Casasent, Carnegie Mellon Univ. (United States)
Sanjan Natarajan, Carnegie Mellon Univ. (United States)

Published in SPIE Proceedings Vol. 2055:
Intelligent Robots and Computer Vision XII: Algorithms and Techniques
David P. Casasent, Editor(s)

© SPIE. Terms of Use
Back to Top