Title :
Solving two-spiral problem through input data encoding
Author :
Chua, H.C. ; Jia, J. ; Chen, L. ; Gong, Y.
Author_Institution :
Sch. of Electr. & Electron. Eng., Nanyang Technol. Inst., Singapore
fDate :
5/11/1995 12:00:00 AM
Abstract :
The authors show that the two-spiral problem can be easily solved using a standard back propagation neural network by properly encoding the raw input data. The authors also examine and compare several data encoding schemes for use in neural networks to improve the training efficiency and generalisation property
Keywords :
backpropagation; neural nets; back propagation neural network; data encoding schemes; generalisation property; input data encoding; raw input data; training efficiency; two-spiral problem;
Journal_Title :
Electronics Letters
DOI :
10.1049/el:19950546
