A functional neural network for computing the largest modulus eigenvalues and their corresponding eigenvectors of an anti-symmetric matrix

Efficient computation of the largest modulus eigenvalues of a real anti-symmetric matrix is a very important problem in engineering. Using a neural network to complete these operations is in an asynchronous manner and can achieve high performance. This paper proposes a functional neural network (FNN) that can be transformed into a complex differential equation to do this work. Firstly, the mathematical analytic solution of the equation is received, and then the convergence properties of this FNN are analyzed. The simulation result indicates that with general initial complex values, the network will converge to the complex eigenvector corresponding to the eigenvalue whose imaginary part is positive, and modulus is the largest of all eigenvalues. Comparing with other neural networks used for computing eigenvalues and eigenvectors, this network is adaptive to real anti-symmetric matrices for completing these operations.

[1]  Li Yanda,et al.  Real-time neural computation of the eigenvector corresponding to the largest eigenvalue of positive matrix , 1995 .

[2]  Arogyaswami Paulraj,et al.  Some Algorithms for Eigensubspace Estimation , 1995 .

[3]  Fa-Long Luo,et al.  A principal component analysis algorithm with invariant norm , 1995, Neurocomputing.

[4]  Renzo Perfetti,et al.  Training Spatially Homogeneous Fully Recurrent Neural Networks in Eigenvalue Space , 1997, Neural Networks.

[5]  Yeung Yam,et al.  Complex recurrent neural network for computing the inverse and pseudo-inverse of the complex matrix , 1998, Appl. Math. Comput..

[6]  He Zhenya,et al.  Neural network approaches for the extraction of the eigenstructure , 1996, Neural Networks for Signal Processing VI. Proceedings of the 1996 IEEE Signal Processing Society Workshop.

[7]  Toshiki Kindo,et al.  Eigenspace Separation of Autocorrelation Memory Matrices for Capacity Expansion , 1997, Neural Networks.

[8]  M. Kobayashi,et al.  Estimation of singular values of very large matrices using random sampling , 2001 .

[9]  Yan Fu,et al.  Neural networks based approach for computing eigenvectors and eigenvalues of symmetric matrix , 2004 .

[10]  Elmar Wolfgang Lang,et al.  A neural implementation of the JADE algorithm (nJADE) using higher-order neurons , 2004, Neurocomputing.

[11]  Fa-Long Luo,et al.  A Minor Component Analysis Algorithm , 1997, Neural Networks.

[12]  Nian Li.  A matrix inverse eigenvalue problem and its application , 1997 .