Title :
A quaternary version of the back-propagation algorithm
Author_Institution :
Electrotech. Lab., Tsukuba, Japan
Abstract :
A quaternary version, of the back-propagation algorithm is proposed for multilayered neural networks whose weights, threshold values, input and output signals are all quaternions. This new algorithm can be used to learn patterns consisted of quaternions in a natural way. An example was used to successfully test the new formulation
Keywords :
backpropagation; multilayer perceptrons; vectors; multilayered neural networks; quaternary back-propagation algorithm; quaternions; threshold values; weights; Cities and towns; Computational modeling; Computer vision; Laboratories; Multi-layer neural network; Neural networks; Neurons; Quaternions; Robot vision systems; Testing;
Conference_Titel :
Neural Networks, 1995. Proceedings., IEEE International Conference on
Conference_Location :
Perth, WA
Print_ISBN :
0-7803-2768-3
DOI :
10.1109/ICNN.1995.488166
