Abstract
We focus on the rank-one approximation problem of a tensor \(\mathcal {A}\in \mathbb {R}^{I_1\times I_2\times \dots \times I_N}\) by neural networks: finding a real scalar σ and N unit \({\mathbf {x}}_n\in \mathbb {R}^{I_n}\) to minimize
where \(x_{n,i_n}\) is the i nth element of \({\mathbf {x}}_n\in \mathbb {R}^{I_n}\) for all i n and n, and σ > 0 is a scaling factor.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
A. Cichocki, R. Unbehauen, Neural Networks for Optimization and Signal Processing (Wiley, New York, 1993)
L. Liao, H. Qi, L. Qi, Neurodynamical optimization. J. Glob. Optim. 28(2), 175–195 (2004)
A. Rodriguezvazquez, R. Dominguezcastro, A. Rueda, J. Huertas, E. Sanchezsinencio, Nonlinear switched capacitor ‘neural’ networks for optimization problems. IEEE Trans. Circuits Syst. 37(3), 384–398 (1990)
A. Cichocki, Neural network for singular value decomposition. Electron. Lett. 28(8), 784–786 (1992)
K. Diamantaras, S. Kung, Cross-correlation neural network models. IEEE Trans. Signal Process. 42(11), 3218–3223 (1994)
D. Feng, Z. Bao, X. Zhang, A cross-associative neural network for SVD of non-squared data matrix in signal processing. IEEE Trans. Neural Netw. 12(5), 1215–1221 (2001)
S. Fiori, Singular value decomposition learning on double stiefel manifold. Int. J. Neural Syst. 13(3), 155–170 (2003)
J. Nie, L. Wang, Semidefinite relaxations for best rank-1 tensor approximations. SIAM J. Matrix Anal. Appl. 35(3), 1155–1179 (2014)
L. Liu, W. Wu, Dynamical system for computing largest generalized eigenvalue, in Lecture Notes in Computer Science, vol. 3971 (Springer, Berlin, 2006), pp. 399–404
L. Liu, H. Shao, D. Nan, Recurrent neural network model for computing largest and smallest generalized eigenvalue. Neurocomputing 71(16), 3589–3594 (2008)
Y. Tang, J. Li, Notes on “Recurrent neural network model for computing largest and smallest generalized eigenvalue”. Neurocomputing 73(4), 1006–1012 (2010)
S. Friedland, G. Ottaviani, The number of singular vector tuples and uniqueness of best rank-one approximation of tensors. Found. Comput. Math. 14(6), 1209–1242 (2014)
L. Lim, Singular values and eigenvalues of tensors: a variational approach, in IEEE CAMSAP 2005: First International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (IEEE, Piscataway, 2005), pp. 129–132
L. Wang, M. Chu, B. Yu, Orthogonal low rank tensor approximation: alternating least squares method and its global convergence. SIAM J. Matrix Anal. Appl. 36(1), 1–19 (2015)
L. De Lathauwer, B. De Moor, J. Vandewalle, On the best rank-1 and rank-(r 1, r 2, ..., r n) approximation of higher-order tensors. SIAM J. Matrix Anal. Appl. 21(4), 1324–1342 (2000)
T. Zhang, G. Golub, Rank-one approximation to high order tensors. SIAM J. Matrix Anal. Appl. 23(2), 534–550 (2001)
S. Friedland, L. Lim, Nuclear norm of higher-order tensors. Math. Comput. 87, 1255–1281 (2018)
J. Nie, Symmetric tensor nuclear norms. SIAM J. Appl. Algebr. Geom. 1–1, 599–625 (2017)
X. Zhang, C. Ling, L. Qi, The best rank-1 approximation of a symmetric tensor and related spherical optimization problems. SIAM J. Matrix Anal. Appl. 33(3), 806–821 (2012)
K. Chang, K. Pearson, T. Zhang, Some variational principles for Z-eigenvalues of nonnegative tensors. Linear Algebra Appl. 438(11), 4166–4182 (2013)
L. Qi, Eigenvalues of a real supersymmetric tensor. J. Symb. Comput. 40(6), 1302–1324 (2005)
E. Kofidis, P. Regalia, On the best rank-1 approximation of higher-order supersymmetric tensors. SIAM J. Matrix Anal. Appl. 23(3), 863–884 (2002)
T. Kolda, J. Mayo, Shifted power method for computing tensor eigenpairs. SIAM J. Matrix Anal. Appl. 32(4), 1095–1124 (2011)
L. Ljung, Analysis of recursive stochastic algorithms. IEEE Trans. Autom. Control 22(4), 551–575 (1977)
M. Che, A. Cichocki, Y. Wei, Neural networks for computing best rank-one approximations of tensors and its applications. Neurocomputing 267(3), 114–133 (2017)
N. Samardzija, R. Waterland, A neural network for computing eigenvectors and eigenvalues. Biol. Cybern. 65(4), 211–214 (1991)
J. Vegas, P. Zufiria, Generalized neural networks for spectral analysis: dynamics and liapunov function. Neural Netw. 17(16), 233–245 (2004)
M. Che, X. Wang, Y. Wei, H. Yan, A collective neurodynamic optimization approach to the low multilinear rank approximation of tensors. Southwestern Univ. Financ. Econ. (2019). Preprint
X. Wang, M. Che, Y. Wei, Neural network for the computation of the best rank-one approximation of the fourth-order partially symmetric tensors. Numer. Math. Theory, Methods Appl. 11, 673–700 (2018)
M. Che, L. Qi, Y. Wei, Perturbation bounds of tensor eigenvalue and singular value problems with even order. Linear Multilinear Algebra 64(4), 622–652 (2016)
C. Van Loan, Generalizing the singular value decomposition. SIAM J. Numer. Anal. 13(1), 76–83 (1976)
Y. Luo, D. Tao, K. Ramamonhanarao, C. Xu, Y. Wen, Tensor canonical correlation analysis for multi-view dimension reduction. IEEE Trans. Knowl. Data Eng. 27(11), 3111–3124 (2015)
G. Golub, C. Van Loan, Matrix Computations, 4th edn. (Johns Hopkins University Press, Baltimore, 2013)
K. Chang, K. Pearson, T. Zhang, On eigenvalue problems of real symmetric tensors. J. Math. Anal. Appl. 350(1), 416–422 (2009)
W. Ding, Y. Wei, Generalized tensor eigenvalue problems. SIAM J. Matrix Anal. Appl. 36(3), 1073–1099 (2015)
T. Kolda, J. Mayo, An adaptive shifted power method for computing generalized tensor eigenpairs. SIAM J. Matrix Anal. Appl. 35(4), 1563–1581 (2014)
L. Qi, The best rank-one approximation ratio of a tensor space. SIAM J. Matrix Anal. Appl. 32(2), 430–442 (2011)
S. Ragnarsson, C. Van Loan, Block tensors and symmetric embeddings. Linear Algebra Appl. 438(2), 853–874 (2013)
D. Chu, L. De Lathauwer, B. De Moor, On the computation of the restricted singular value decomposition via the cosine-sine decomposition. SIAM J. Matrix Anal. Appl. 22(2), 580–601 (2000)
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this chapter
Cite this chapter
Che, M., Wei, Y. (2020). Neural Networks. In: Theory and Computation of Complex Tensors and its Applications. Springer, Singapore. https://doi.org/10.1007/978-981-15-2059-4_6
Download citation
DOI: https://doi.org/10.1007/978-981-15-2059-4_6
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-2058-7
Online ISBN: 978-981-15-2059-4
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)