Structure of learning in the complex numbered back-propagation network

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.<
>