18 June 2015 Experimental analysis of a Lotka-Volterra neural network for classification
Author Affiliations +
Abstract
An experimental study of a neural network modeled by an adaptive Lotka-Volterra system follows. With totally inhibitory connections, this system can be embedded in a simple classification network. This network is able to classify and monitor its inputs in a spontaneous nonlinear fashion without prior training. We describe a framework for leveraging this behavior through an example involving breast cancer diagnosis.
© (2015) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Christopher L. Sukhu, Christopher L. Sukhu, Joseph Stanton, Joseph Stanton, Marc Aylesworth, Marc Aylesworth, } "Experimental analysis of a Lotka-Volterra neural network for classification", Proc. SPIE 9494, Next-Generation Robotics II; and Machine Intelligence and Bio-inspired Computation: Theory and Applications IX, 94940N (18 June 2015); doi: 10.1117/12.2177214; https://doi.org/10.1117/12.2177214
PROCEEDINGS
6 PAGES


SHARE
RELATED CONTENT

Representing Shape Primitives In Neural Networks
Proceedings of SPIE (August 22 1988)
Unsupervised training of structuring elements
Proceedings of SPIE (July 01 1991)
Learning tree: a new concept in learning
Proceedings of SPIE (September 01 1993)
Hardware neural network on an SOPC platform
Proceedings of SPIE (October 30 2009)

Back to Top