Title :
Characterization of network responses to known, unknown, and ambiguous inputs
Author :
Hellstrom, Benjamin ; Brinsley, Jim
Author_Institution :
Analysis & Technology, Inc., Arlington, VA, USA
Abstract :
Neural networks typically classify patterns by mapping the input feature space to the corners of the m-dimensional unit hypercube where m is the number of output classes. When classifier networks of graded threshold neurons are presented with patterns that are strong, ambiguous, or unknown, characteristic responses are emitted. A second tier network can be used to characterize the decision of the classifier network. By using a class count-independent mapping as an intermediary, a training set of unknowns can be generated for training the second tier. The two tiered approach is described and the internal function of the second tier is analyzed
Keywords :
hypercube networks; learning (artificial intelligence); neural nets; pattern recognition; characteristic responses; classifier networks; count-independent mapping; graded threshold neurons; hypercube; input feature space; internal function; network responses; neural networks; pattern classifier; Costs; Electronic mail; Filters; Hypercubes; Neural networks; Neurons; Pattern recognition; Road transportation; Space technology; Utility programs;
Conference_Titel :
Neural Networks for Processing [1993] III. Proceedings of the 1993 IEEE-SP Workshop
Conference_Location :
Linthicum Heights, MD
Print_ISBN :
0-7803-0928-6
DOI :
10.1109/NNSP.1993.471866
