Title :
The K-Nearest Neighbor Attractor-based Neural Network and the Optimal Linear Discriminatory Filter Classifier
Author :
Dobeck, Gerald J.
Author_Institution :
Naval Surface Warfare Center, Panama City, FL
Abstract :
The K-Nearest Neighbor Attractor-based Neural Network and the Optimal Linear Discriminatory Filter Classifier are feature-based classifiers that are trained via supervised learning using a training set of feature vectors. They were developed by the author and successfully used in several applications where they were "and-ed." Results using these classifiers have been published, but comprehensive descriptions of them have not appeared in the literature. This paper presents their detailed descriptions
Keywords :
learning (artificial intelligence); neural nets; K-Nearest Neighbor Attractor; Neural Network; Optimal Linear Discriminatory Filter Classifier; feature vectors; feature-based classifiers; supervised learning; Cities and towns; Eigenvalues and eigenfunctions; Histograms; Neural networks; Nonlinear filters; Performance evaluation; Statistics; Supervised learning; Training data; Vectors;
Conference_Titel :
OCEANS 2006
Conference_Location :
Boston, MA
Print_ISBN :
1-4244-0114-3
Electronic_ISBN :
1-4244-0115-1
DOI :
10.1109/OCEANS.2006.307017
