Title :
Calibrating the performance of neural networks
Author :
Barton, R. ; Fogel, D.B. ; Krieger, A.
Author_Institution :
Orincon Corp., San Diego, CA, USA
Abstract :
The authors offer a procedure to assess the performance of signal classifiers, including neural networks. An example is described wherein three neural classifiers are tested in their ability to discriminate between a modeled underwater man-made event, real clutter signals, and a modeled quiet ocean background. Empirical studies using neural classifiers on ocean acoustic data are described. Some observations regarding the utility of the outline procedure are offered
Keywords :
acoustic signal processing; neural nets; underwater sound; neural classifiers; neural networks; ocean acoustic data; signal classifiers; Acoustic measurements; Background noise; Linearity; Network topology; Neural networks; Oceans; Sea measurements; Signal detection; Signal to noise ratio; Training data;
Conference_Titel :
Neural Networks for Ocean Engineering, 1991., IEEE Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-0205-2
DOI :
10.1109/ICNN.1991.163372
