Abstract
The paper describes a parallel feed-forward neural network training algorithm based on the QR decomposition with the use of the Givens rotation. The beginning brings a brief mathematical background on Givens rotation matrices and elimination step. Then the error criterion and its necessary transformations for the QR decomposition are presented. The paper’s core holds an essential explanation to accomplish hardware-based parallel implementation. The paper concludes with a theoretical description of speed improvement gained by parallel implementation of the Givens reduction in the QR decomposition process.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Starczewski, A.: A clustering method based on the modified RS validity index. In: Rutkowski, L., Korytkowski, M., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2013. LNCS, vol. 7895, pp. 242–250. Springer, Heidelberg (2013). doi:10.1007/978-3-642-38610-7_23
Starczewski, A.: A new validity index for crisp clusters. Pattern Anal. Appl. (2015)
Starczewski, A., Krzyżak, A.: A modification of the silhouette index for the improvement of cluster validity assessment. In: Rutkowski, L., Korytkowski, M., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2016. LNCS, vol. 9693, pp. 114–124. Springer, Cham (2016). doi:10.1007/978-3-319-39384-1_10
Bilski, J., Smoląg, J., Galushkin, A.I.: The parallel approach to the conjugate gradient learning algorithm for the feedforward neural networks. In: Rutkowski, L., Korytkowski, M., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2014. LNCS(LNAI), vol. 8467, pp. 12–21. Springer, Cham (2014). doi:10.1007/978-3-319-07173-2_2
Bilski, J.: Momentum modification of the RLS algorithms. In: Rutkowski, L., Siekmann, J.H., Tadeusiewicz, R., Zadeh, L.A. (eds.) ICAISC 2004. LNCS, vol. 3070, pp. 151–157. Springer, Heidelberg (2004). doi:10.1007/978-3-540-24844-6_18
Bilski, J.: Struktury rwnolege dla jednokierunkowych i dynamicznych sieci neuronowych. Akademicka Oficyna Wydawnicza EXIT, Warszawa (2013)
Bilski, J., Kowalczyk, B., Żurada, J.M.: Application of the givens rotations in the neural network learning algorithm. In: Rutkowski, L., Korytkowski, M., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2016. LNCS(LNAI), vol. 9692, pp. 46–56. Springer, Cham (2016). doi:10.1007/978-3-319-39378-0_5
Bilski, J., Wilamowski, B.M.: Parallel learning of feedforward neural networks without error backpropagation. In: Rutkowski, L., Korytkowski, M., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2016. LNCS(LNAI), vol. 9692, pp. 57–69. Springer, Cham (2016). doi:10.1007/978-3-319-39378-0_6
Bilski, J., Smoląg, J., Żurada, J.M.: Parallel approach to the levenberg- marquardt learning algorithm for feedforward neural networks. In: Rutkowski, L., Korytkowski, M., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2015. LNCS(LNAI), vol. 9119, pp. 3–14. Springer, Cham (2015). doi:10.1007/978-3-319-19324-3_1
Bilski, J., Rutkowski, L.: Numerically robust learning algorithms for feed forward neural networks. In: Rutkowski, L., Kacprzyk, J. (eds.) Neural Networks and Soft Computing. Advances in Soft Computing, pp. 149–154. Physica-Verlag, Heidelberg (2003)
Bilski, J., Smoląg, J.: Parallel approach to learning of the recurrent jordan neural network. In: Rutkowski, L., Korytkowski, M., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2013. LNCS(LNAI), vol. 7894, pp. 32–40. Springer, Heidelberg (2013). doi:10.1007/978-3-642-38658-9_3
Werbos, J.: Beyond Regression: New Tools for Prediction and Analysis in the Behavioral Sciences. Harvard University (1974)
Nowicki, R.K., Nowak, B.A., Starczewski, J.T., Cpalka, K.: The learning of neuro-fuzzy approximator with fuzzy rough sets in case of missing features. In: 2014 International Joint Conference on Neural Networks (IJCNN), pp. 3759–3766, July 2014
Bilski, J., Rutkowski, L.: A fast training algorithm for neural networks. IEEE Trans. Circ. Syst. Part II 45, 749–753 (1998)
Zalasiński, M., Łapa, K., Cpałka, K.: New algorithm for evolutionary selection of the dynamic signature global features. In: Rutkowski, L., Korytkowski, M., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2013. LNCS (LNAI), vol. 7895, pp. 113–121. Springer, Heidelberg (2013). doi:10.1007/978-3-642-38610-7_11
Zalasiński, M., Cpałka, K., Rakus-Andersson, E.: An idea of the dynamic signature verification based on a hybrid approach. In: Rutkowski, L., Korytkowski, M., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2016. LNCS (LNAI), vol. 9693, pp. 232–246. Springer, Cham (2016). doi:10.1007/978-3-319-39384-1_21
Zalasiński, M., Cpałka, K., Hayashi, Y.: New method for dynamic signature verification based on global features. In: Rutkowski, L., Korytkowski, M., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2014. LNCS, vol. 8468, pp. 231–245. Springer, Cham (2014). doi:10.1007/978-3-319-07176-3_21
Zalasiński, M., Cpałka, K., Hayashi, Y.: A new approach to the dynamic signature verification aimed at minimizing the number of global features. In: Rutkowski, L., Korytkowski, M., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2016. LNCS (LNAI), vol. 9693, pp. 218–231. Springer, Cham (2016). doi:10.1007/978-3-319-39384-1_20
Mleczko, W.K., Kapuściński, T., Nowicki, R.K.: Rough deep belief network - application to incomplete handwritten digits pattern classification. In: Dregvaite, G., Damasevicius, R. (eds.) ICIST 2015. CCIS, vol. 538, pp. 400–411. Springer, Cham (2015). doi:10.1007/978-3-319-24770-0_35
Nowak, B.A., Nowicki, R.K., Starczewski, J.T., Marvuglia, A.: The learning of neuro-fuzzy classifier with fuzzy rough sets for imprecise datasets. In: Rutkowski, L., Korytkowski, M., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2014. LNCS (LNAI), vol. 8467, pp. 256–266. Springer, Cham (2014). doi:10.1007/978-3-319-07173-2_23
Tadeusiewicz, R.: Sieci Neuronowe. Akademicka Oficyna Wydawnicza, Warszawa (1993)
Nowak, B.A., Nowicki, R.K.: Learning in rough-neuro-fuzzy system for data with missing values. In: Wyrzykowski, R., Dongarra, J., Karczewski, K., Waśniewski, J. (eds.) PPAM 2011. LNCS, vol. 7203, pp. 501–510. Springer, Heidelberg (2012). doi:10.1007/978-3-642-31464-3_51
Knop, M., Kapuscinski, T., Mleczko, W.K.: Video key frame detection based on the restricted boltzmann machine. J. Appl. Math. Comput. Mech. 14(3), 49–58 (2015)
Wozniak, M., Polap, D., Nowicki, R.K., Napoli, C., Pappalardo, G., Tramontana, E.: Novel approach toward medical signals classifier. In: 2015 International Joint Conference on Neural Networks (IJCNN), pp. 1–7, July 2015
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Bilski, J., Kowalczyk, B., Żurada, J.M. (2017). Parallel Implementation of the Givens Rotations in the Neural Network Learning Algorithm. In: Rutkowski, L., Korytkowski, M., Scherer, R., Tadeusiewicz, R., Zadeh, L., Zurada, J. (eds) Artificial Intelligence and Soft Computing. ICAISC 2017. Lecture Notes in Computer Science(), vol 10245. Springer, Cham. https://doi.org/10.1007/978-3-319-59063-9_2
Download citation
DOI: https://doi.org/10.1007/978-3-319-59063-9_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-59062-2
Online ISBN: 978-3-319-59063-9
eBook Packages: Computer ScienceComputer Science (R0)