DocumentCode :
3272787
Title :
Backpropagation decision region formation properties
Author :
Svedlow, M.
fYear :
1989
fDate :
0-0 1989
Abstract :
Summary form only given, as follows. An experimental analysis was performed to determine decision region formation properties of the backpropagation (BP) paradigm for a ´winner-take-all´ network using sparse training sets. Key objectives were to determine whether supervised training using the BP paradigm would result in nearest neighbor decision regions, and whether the resulting region boundaries were independent of the initial conditions of the network link weights. Using a three-layer network (i.e. an input layer, an output layer, and a single hidden layer), the experiments showed that the convergent decision regions were not necessarily nearest-neighbor solutions, nor were the regions necessarily independent of the starting condition. These results suggest precautions in designing adaptive networks, especially for high-dimensional networks (i.e. more than two input/output units) where the decision regions are not easily visualized.<>
Keywords :
adaptive systems; learning systems; neural nets; adaptive networks; backpropagation; decision region formation properties; high-dimensional networks; nearest neighbor decision regions; network link weights; paradigm; sparse training sets; supervised training; three-layer network; Adaptive systems; Learning systems; Neural networks;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 1989. IJCNN., International Joint Conference on
Conference_Location :
Washington, DC, USA
Type :
conf
DOI :
10.1109/IJCNN.1989.118537
Filename :
118537
Link To Document :
بازگشت