论文信息 - On the critical points of the complex-valued neural network

On the critical points of the complex-valued neural network

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.

Tohru Nitta | T. Nitta

[1] Héctor J. Sussmann,et al. Uniqueness of the weights for minimal feedforward nets with a given input-output map , 1992, Neural Networks.

[2] Tohru Nitta,et al. An Extension of the Back-Propagation Algorithm to Complex Numbers , 1997, Neural Networks.

[3] Tohru Nitta,et al. Redundancy of the parameters of the complex-valued neural network , 2002, Neurocomputing.

[4] Francesco Piazza,et al. On the complex backpropagation algorithm , 1992, IEEE Trans. Signal Process..

[5] Tohru Nitta. On the inherent property of the decision boundary in complex-valued neural networks , 2003, Neurocomputing.

[6] Clark C. Guest,et al. Modification of backpropagation networks for complex-valued signal processing in frequency domain , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

[7] Kenji Fukumizu,et al. Local minima and plateaus in hierarchical structures of multilayer perceptrons , 2000, Neural Networks.

[8] Cris Koutsougeras,et al. Complex domain backpropagation , 1992 .