Abstract
In this paper a method of faster training of the ensembles of the tensor classifiers based on the Higher-Order Singular Value Decomposition is presented. The method relies on the fixed-point method of eigenvector computation which is employed at the stage of subspace construction of the flattened versions of the input tensor patterns. As verified experimentally, the proposed method allows up to five times speed-up factor at no significant difference in accuracy.
References
Bingham E., Hyvärinen A.: A fast fixed-point algorithm for independent component analysis of complex valued signals. Int. J. Neural Syst. 10(1) (2000). World Scientic Publishing Company
Cyganek, B.: Ensemble of Tensor Classifiers Based on the Higher-Order Singular Value Decomposition. HAIS 2012, Part II, LNCS, vol. 7209, pp. 578–589. Springer (2012)
Cyganek B.: Embedding of the Extended Euclidean Distance into Pattern Recognition with Higher-Order Singular Value Decomposition of Prototype Tensors. In: Cortesi, A., et al. (eds.) IFIP International Federation for Information Processing, Venice, Italy CISIM 2012, Lecture Notes in Computer Science LNCS, vol. 7564, pp. 180–190. Springer (2012)
Cyganek, B.: Object Detection and Recognition in Digital Images: Theory and Practice. Wiley (2013)
Cyganek B., Krawczyk B., Woźniak, M.: Multidimensional data classification with chordal distance based kernel and support vector machines. Engineering Applications of Artificial Intelligence, Part A, vol. 46, pp. 10–22. Elsevier (2015)
Cyganek, B., Woźniak, M.: An improved vehicle logo recognition using a classifier ensemble based on pattern tensor representation and decomposition. New Gener. Comput. Springer 33(4), 389–408 (2015)
Demmel J.W.: Applied Numerical Linear Algebra. Siam (1997)
Grandvalet, Y.: Bagging equalizes influence. Mach. Learn. 55, 251–270 (2004)
Hull, J.: A database for handwritten text recognition research. IEEE Trans. Pattern Anal. Mach. Intell. 16(5), 550–554 (1994)
Kolda, T.G., Bader, B.W.: Tensor decompositions and applications. SIAM Rev. 455–500 (2008)
Krawczyk, B.: One-class classifier ensemble pruning and weighting with firefly algorithm. Neurocomputing 150, 490–500 (2015)
de Lathauwer, L.: Signal Processing Based on Multilinear Algebra. Ph.D. dissertation, Katholieke Universiteit Leuven (1997)
de Lathauwer, L., de Moor, B., Vandewalle, J.: A multilinear singular value decomposition. SIAM J. Matrix Anal. Appl. 21(4), 1253–1278 (2000)
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-Based learning applied to document recognition. In: Proceedings of IEEE on Speech & Image Processing, vol. 86, No. 11, pp. 2278–2324 (1998)
Marot J., Fossati C., Bourennane S.: About advances in tensor data denoising methods. EURASIP J. Adv. Sig. Process. (2008)
Savas, B., Eldén, L.: Handwritten digit classification using higher order singular value decomposition. Pattern Recogn. 40, 993–1003 (2007)
Woźniak, M., Grana, M., Corchado, E.: A survey of multiple classifier systems as hybrid systems. Inf. Fusion 16(1), 3–17 (2014)
Acknowledgement
This work was supported by the Polish National Science Centre under the grant no. DEC-2014/15/B/ST6/00609. This work was supported by EC under FP7, Coordination and Support Action, Grant Agreement Number 316097, ENGINE—European Research Centre of Network Intelligence for Innovation Enhancement (http://engine.pwr.wroc.pl/). All computer experiments were carried out using computer equipment sponsored by ENGINE project.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this paper
Cite this paper
Cyganek, B., Woźniak, M. (2016). On Robust Computation of Tensor Classifiers Based on the Higher-Order Singular Value Decomposition. In: Silhavy, R., Senkerik, R., Oplatkova, Z.K., Silhavy, P., Prokopova, Z. (eds) Software Engineering Perspectives and Application in Intelligent Systems. ICTIS CSOC 2017 2016. Advances in Intelligent Systems and Computing, vol 465. Springer, Cham. https://doi.org/10.1007/978-3-319-33622-0_18
Download citation
DOI: https://doi.org/10.1007/978-3-319-33622-0_18
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-33620-6
Online ISBN: 978-3-319-33622-0
eBook Packages: EngineeringEngineering (R0)