Complex domain backpropagation
- 1 May 1992
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems II: Analog and Digital Signal Processing
- Vol. 39 (5), 330-334
- https://doi.org/10.1109/82.142037
Abstract
The backpropagation algorithm is extended to complex domain backpropagation (CDBP) which can be used to train neural networks for which the inputs, weights, activation functions, and outputs are complex-valued. Previous derivations of CDBP were necessarily admitting activation functions that have singularities, which is highly undesirable. In the derivation, CDBP is derived so that that it accommodates classes of suitable activation functions. One such function is found and the circuit implementation of the corresponding neuron is given. CDBP hardware circuits can be used to process sinusoidal signals all at the same frequency (phasors).Keywords
This publication has 4 references indexed in Scilit:
- The complex backpropagation algorithmIEEE Transactions on Signal Processing, 1991
- Modification of backpropagation networks for complex-valued signal processing in frequency domainPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1990
- Adaptive filtering in the frequency domainProceedings of the IEEE, 1978
- The complex LMS algorithmProceedings of the IEEE, 1975