Title :
Structure of learning in the complex numbered back-propagation network
Author_Institution :
Electrotech. Lab., Ibaraki, Japan
fDate :
27 Jun-2 Jul 1994
Abstract :
The characteristics of the learning rule in the “Complex-BP” a complex numbered version of the backpropagation algorithm, are investigated. The results of this study may be summarized as follows: the error backpropagation has a structure which is concerned with two dimensional motion; the unit of learning is complex valued signals flowing in neural networks; the learning rule is structured to avoid a “standstill in learning”. Ultimately, learning speed is improved. In addition, the number of parameters needed is only about half that of the standard BP
Keywords :
backpropagation; feedforward neural nets; signal processing; Complex-BP; backpropagation algorithm; complex numbered back-propagation network; complex numbered version; complex valued signals; error backpropagation; learning rule; learning speed; two dimensional motion; Cities and towns; Clocks; Convergence; Equations; Intelligent networks; Multi-layer neural network; Neural networks; Neurons;
Conference_Titel :
Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-1901-X
DOI :
10.1109/ICNN.1994.374173
