Title :
Distributed coding for data representation of back-propagation neural network classifiers
Author :
Chong, C.C. ; Jia, J.C.
Author_Institution :
Sch. of Electr. & Electron. Eng., Nanyang Technol. Inst.
fDate :
10/12/1995 12:00:00 AM
Abstract :
A new distributed input coding is derived by distributing the feature variables over a number of input nodes based on the distribution of the training data. Using this coding method representation. The range of each input node will be fully optimised: this enables the network to converge at a higher rate during training. The coding method also enables the network to maintain the generalisation capability of conventional normalisation coding
Keywords :
backpropagation; encoding; feature extraction; neural nets; pattern classification; back-propagation neural network classifiers; coding method representation; data representation; distributed coding; feature variables; generalisation capability; input nodes; training;
Journal_Title :
Electronics Letters
