Title :
Continuous complex-valued back-propagation learning
Author_Institution :
Tokyo Univ., Japan
Abstract :
A novel back-propagation learning method is proposed for fully complex-valued layered neural networks. Nonlinearity suitable for realising smooth and unified complex learning is introduced. A gradient descent method is also analysed and optimised so that the variations of independent elements of the output complex vectors are related directly to the fragmentary changes of weighting matrix elements. The learning process is presented and demonstrated.
Keywords :
learning systems; neural nets; vectors; back-propagation learning method; complex learning; complex-valued layered neural networks; gradient descent method; output complex vectors; weighting matrix elements;
Journal_Title :
Electronics Letters
DOI :
10.1049/el:19921186
