A Unified Self-Stabilizing Neural Network Algorithm for Principal Takagi Component Extraction

In this paper, we develop efficient methods for the computation of the Takagi components and the Takagi subspaces of complex symmetric matrices via the complex-valued neural network models. Firstly, we present a unified self-stabilizing neural network learning algorithm for principal Takagi components and study the stability of the proposed unified algorithms via the fixed-point analysis method. Secondly, the unified algorithm for extracting principal Takagi components is generalized to compute the principal Takagi subspace. Thirdly, we prove that the associated differential equations will globally asymptotically converge to an invariance set and the corresponding energy function attains a unique global minimum if and only if its state matrices span the principal Takagi subspace. Finally, numerical simulations are carried out to illustrate the theoretical results.

[1]  Y. Rui,et al.  Learning to Rank Using User Clicks and Visual Features for Image Retrieval , 2015, IEEE Transactions on Cybernetics.

[2]  Yimin Wei,et al.  Adaptive algorithms for computing the principal Takagi vector of a complex symmetric matrix , 2018, Neurocomputing.

[3]  W. Gragg,et al.  Singular value decompositions of complex symmetric matrices , 1988 .

[4]  Zengyun Wang,et al.  Dynamical Behavior of Complex-Valued Hopfield Neural Networks with Discontinuous Activation Functions , 2017, Neural Processing Letters.

[5]  Jun Yu,et al.  Multimodal Face-Pose Estimation With Multitask Manifold Deep Learning , 2019, IEEE Transactions on Industrial Informatics.

[6]  Pablo Sanchis,et al.  Analytical Design Methodology for Litz-Wired High-Frequency Power Transformers , 2015, IEEE Transactions on Industrial Electronics.

[7]  Akira Hirose,et al.  Complex-Valued Neural Networks , 2006, Studies in Computational Intelligence.

[8]  M. Bohner,et al.  Global Stability of Complex-Valued Neural Networks on Time Scales , 2011 .

[9]  Glenn Schober,et al.  Univalent Functions - Selected Topics , 1975 .

[10]  Alex D. Bain,et al.  Chemical Exchange in NMR , 2003 .

[11]  Claudio Moraga,et al.  Identification of Lags in Nonlinear Autoregressive Time Series Using a Flexible Fuzzy Model , 2015, Neural Processing Letters.

[12]  Igor N. Aizenberg,et al.  Complex-Valued Neural Networks with Multi-Valued Neurons , 2011, Studies in Computational Intelligence.

[13]  Wei Xing Zheng,et al.  A complex-valued neural dynamical optimization approach and its stability analysis , 2015, Neural Networks.

[14]  Meng Wang,et al.  Multimodal Deep Autoencoder for Human Pose Recovery , 2015, IEEE Transactions on Image Processing.

[15]  Gene H. Golub,et al.  Matrix computations , 1983 .

[16]  Ralf Möller,et al.  A Self-Stabilizing Learning Rule for Minor Component Analysis , 2004, Int. J. Neural Syst..

[17]  Ken Kreutz-Delgado,et al.  The Complex Gradient Operator and the CR-Calculus ECE275A - Lecture Supplement - Fall 2005 , 2009, 0906.4835.

[18]  Jun Yu,et al.  Local Deep-Feature Alignment for Unsupervised Dimension Reduction , 2018, IEEE Transactions on Image Processing.

[19]  L. Trefethen.  Near-circularity of the error curve in complex Chebyshev approximation , 1981 .

[20]  Di Wang,et al.  Novel Self-Organizing Takagi Sugeno Kang Fuzzy Neural Networks Based on ART-like Clustering , 2004, Neural Processing Letters.

[21]  Léon Autonne,et al.  Sur les matrices hypohermitiennes et sur les matrices unitaires , 1915 .

[22]  Qingming Huang,et al.  Spatial Pyramid-Enhanced NetVLAD With Weighted Triplet Loss for Place Recognition , 2020, IEEE Transactions on Neural Networks and Learning Systems.

[23]  Jun Yu,et al.  Click Prediction for Web Image Reranking Using Multimodal Sparse Coding , 2014, IEEE Transactions on Image Processing.

[24]  A. Bos.  Complex gradient and Hessian , 1994 .

[25]  Jun Yu,et al.  Multitask Autoencoder Model for Recovering Human Poses , 2018, IEEE Transactions on Industrial Electronics.

[26]  P. Goldbart,et al.  Geometric measure of entanglement and applications to bipartite and multipartite quantum states , 2003, quant-ph/0307219.

[27]  Jun Yu,et al.  Image-Based 3D Human Pose Recovery with Locality Sensitive Sparse Retrieval , 2013, 2013 IEEE International Conference on Systems, Man, and Cybernetics.

[28]  B. A. D. H. Brandwood.  A complex gradient operator and its applica-tion in adaptive array theory , 1983 .

[29]  S. Qiao,et al.  Generalized Inverses: Theory and Computations , 2018 .

[30]  George Lindfield,et al.  Numerical Methods Using MATLAB , 1998 .

[31]  Seungjin Choi,et al.  Independent Component Analysis , 2009, Handbook of Natural Computing.

[32]  Pierre Comon,et al.  Independent component analysis, A new concept? , 1994, Signal Process..

[33]  Jonas Schreiber.  Complex Valued Neural Networks Utilizing High Dimensional Parameters , 2016 .

[34]  Yuan Yan Tang,et al.  High-Order Distance-Based Multiview Stochastic Learning in Image Classification , 2014, IEEE Transactions on Cybernetics.

[35]  Chongzhao Han,et al.  A Unified Self-Stabilizing Neural Network Algorithm for Principal and Minor Components Extraction , 2012, IEEE Transactions on Neural Networks and Learning Systems.

[36]  Wei Xu,et al.  A twisted factorization method for symmetric SVD of a complex symmetric tridiagonal matrix , 2009, Numer. Linear Algebra Appl..

[37]  Yan Liu,et al.  A Split-Complex Valued Gradient-Based Descent Neuro-Fuzzy Algorithm for TS System and Its Convergence , 2018, Neural Processing Letters.

[38]  Jun Wang,et al.  A Complex-Valued Projection Neural Network for Constrained Optimization of Real Functions in Complex Variables , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[39]  Yimin Wei,et al.  Geometric measures of entanglement in multipartite pure states via complex-valued neural networks , 2018, Neurocomputing.

[40]  Akira Hirose,et al.  Complex-Valued Neural Networks: Theories and Applications , 2003 .

[41]  Tamer Basar,et al.  Analysis of Recursive Stochastic Algorithms , 2001 .

[42]  Yimin Wei,et al.  Iterative algorithms for computing US- and U-eigenpairs of complex tensors , 2017, J. Comput. Appl. Math..

[43]  Huamin Wang,et al.  Exponential Stability of Complex-Valued Memristive Recurrent Neural Networks , 2017, IEEE Transactions on Neural Networks and Learning Systems.

[44]  Yimin Wei,et al.  Complex-valued neural networks for the Takagi vector of complex symmetric matrices , 2017, Neurocomputing.

[45]  Teiji Takagi,et al.  On an Algebraic Problem Reluted to an Analytic Theorem of Carathéodory and Fejér and on an Allied Theorem of Landau , 1924 .

[46]  Sabine Van Huffel,et al.  Enhanced resolution based on minimum variance estimation and exponential data modeling , 1993, Signal Process..

[47]  Abhishek K Gupta,et al.  Numerical Methods using MATLAB , 2014, Apress.

[48]  Wei Xu,et al.  A Divide-and-Conquer Method for the Takagi Factorization , 2008, SIAM J. Matrix Anal. Appl..