On the critical points of the complex-valued neural network
Author:
- 23 April 2004
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 3, 1099-1103
Abstract
The properties of the critical points caused by the hierarchical structure of complex-valued neural networks are investigated. If the loss function used is not regular as a complex function, the critical points caused by the hierarchical structure are all saddle points.Keywords
This publication has 8 references indexed in Scilit:
- On the inherent property of the decision boundary in complex-valued neural networksNeurocomputing, 2003
- Redundancy of the parameters of the complex-valued neural networkNeurocomputing, 2002
- Local minima and plateaus in hierarchical structures of multilayer perceptronsNeural Networks, 2000
- An Extension of the Back-Propagation Algorithm to Complex NumbersNeural Networks, 1997
- Uniqueness of the weights for minimal feedforward nets with a given input-output mapNeural Networks, 1992
- Complex domain backpropagationIEEE Transactions on Circuits and Systems II: Analog and Digital Signal Processing, 1992
- On the complex backpropagation algorithmIEEE Transactions on Signal Processing, 1992
- Modification of backpropagation networks for complex-valued signal processing in frequency domain1990