Classifier neural net with complex-valued weights and square-law nonlinearities

David P. Casasent; Sanjan Natarajan

doi:10.1117/12.150175

20 August 1993 Classifier neural net with complex-valued weights and square-law nonlinearities

David P. Casasent, Sanjan Natarajan

Proceedings Volume 2055, Intelligent Robots and Computer Vision XII: Algorithms and Techniques; (1993) https://doi.org/10.1117/12.150175
Event: Optical Tools for Manufacturing and Advanced Automation, 1993, Boston, MA, United States

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 (P_C). 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.

Citation Download Citation

David P. Casasent and Sanjan Natarajan "Classifier neural net with complex-valued weights and square-law nonlinearities", Proc. SPIE 2055, Intelligent Robots and Computer Vision XII: Algorithms and Techniques, (20 August 1993); https://doi.org/10.1117/12.150175

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available