Title :
A back-propagation algorithm for complex numbered neural networks
Author_Institution :
Electrotech. Lab., Ibaraki, Japan
Abstract :
This paper introduces a complex numbered version of the backpropagation algorithm, which can be applied to neural networks whose weights, threshold values, input and output signals are all complex numbers. This new algorithm can be used to learn complex numbered patterns in a natural way. We show that "complex-BP" can transform geometrical figures.
Keywords :
backpropagation; computational geometry; neural nets; pattern classification; transforms; backpropagation algorithm; complex numbered neural networks; complex numbers; geometrical figures; input and output signals; pattern learning; threshold values; weights; Cities and towns; Equations; Joining processes; Laboratories; Multi-layer neural network; Neural networks; Neurons;
Conference_Titel :
Neural Networks, 1993. IJCNN '93-Nagoya. Proceedings of 1993 International Joint Conference on
Print_ISBN :
0-7803-1421-2
DOI :
10.1109/IJCNN.1993.716968
