2 February 1993 Piecewise quadratic optical neural network
Author Affiliations +
Abstract
A neural network pattern classifier is presented. Its decision boundaries are formed from segments of conic sections which allows it to achieve improved performance over piecewise linear neural network classifiers, such as our earlier adaptive clustering neural network (ACNN). We discuss an optical realization that uses complex-valued weights, optical intensity detectors, and an additional input neuron to achieve piecewise conic decision surfaces (rather than the piecewise linear surfaces that the ACNN produces).
© (1993) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Sanjay S. Natarajan, David P. Casasent, "Piecewise quadratic optical neural network", Proc. SPIE 1773, Photonics for Computers, Neural Networks, and Memories, (2 February 1993); doi: 10.1117/12.983199; https://doi.org/10.1117/12.983199
PROCEEDINGS
PAGES


SHARE
Back to Top