Abstract
Matrix-Vector multiplications usually represent the dominant part of computational operations needed to propagate information through a neural network. This number of operations can be reduced if the weight matrices are structured. In this paper, we introduce a training algorithm for neural networks with sequentially semiseparable weight matrices based on the backpropagation algorithm. By exploiting the structures in the weight matrices, the computational complexity for computing the matrix-vector product can be reduced to the subquadratic domain. We show that this can lead to computing time reductions on a microcontroller. Furthermore, we analyze the generalization capabilities of neural networks with sequentially semiseparable matrices. Our experiments show that neural networks with structured weight matrices can outperform standard feed-forward neural networks in terms of test prediction accuracy for several real-world datasets.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Alimoglu, F., Alpaydin, E.: Methods of combining multiple classifiers based on different representations for pen-based handwritten digit recognition. In: Proceedings of the Fifth Turkish Artificial Intelligence and Artificial Neural Networks Symposium (TAINN 1996). Citeseer (1996)
Chandrasekaran, S., Gu, M., Pals, T.: A fast ULV decomposition solver for hierarchically semiseparable representations. SIAM J. Matrix Anal. Appl. 28(3), 603–622 (2006)
Denil, M., Shakibi, B., Dinh, L., De Freitas, N., et al.: Predicting parameters in deep learning. In: Advances in Neural Information Processing Systems, pp. 2148–2156 (2013)
Dewilde, P., Van der Veen, A.J.: Time-Varying Systems and Computations. Springer, New York (1998). https://doi.org/10.1007/978-1-4757-2817-0
Fan, Y., Lin, L., Ying, L., Zepeda-Núnez, L.: A multiscale neural network based on hierarchical matrices. Multisc. Model. Simul. 17(4), 1189–1213 (2019)
Gantmakher, F., Krein, M.: Sur les matrices completement non négatives et oscillatoires. Compos. Math. 4, 445–476 (1937)
Gardner, A., Kanno, J., Duncan, C.A., Selmic, R.: Measuring distance between unordered sets of different sizes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 137–143 (2014)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Ioannou, Y., Robertson, D., Shotton, J., Cipolla, R., Criminisi, A.: Training CNNs with low-rank filters for efficient image classification. arXiv preprint arXiv:1511.06744 (2015)
Kung, S., Lin, D.: Optimal Hankel-norm model reductions: multivariable systems. IEEE Trans. Autom. Control 26(4), 832–852 (1981)
Lebedev, V., Ganin, Y., Rakhuba, M., Oseledets, I., Lempitsky, V.: Speeding-up convolutional neural networks using fine-tuned cp-decomposition. arXiv preprint arXiv:1412.6553 (2014)
Sindhwani, V., Sainath, T., Kumar, S.: Structured transforms for small-footprint deep learning. In: Advances in Neural Information Processing Systems, pp. 3088–3096 (2015)
Tai, C., Xiao, T., Zhang, Y., Wang, X., et al.: Convolutional neural networks with low-rank regularization. arXiv preprint arXiv:1511.06067 (2015)
Thomas, A.T., Gu, A., Dao, T., Rudra, A., Ré, C.: Learning compressed transforms with low displacement rank. Adv. Neural. Inf. Process. Syst. 2018, 9052 (2018)
Titti, A., Squartini, S., Piazza, F.: A new time-variant neural based approach for nonstationary and non-linear system identification. In: 2005 IEEE International Symposium on Circuits and Systems, pp. 5134–5137. IEEE (2005)
Van Lint, J., Hoogendoorn, S., van Zuylen, H.J.: Accurate freeway travel time prediction with state-space neural networks under missing data. Transp. Rese. Part C: Emerg. Technol. 13(5–6), 347–369 (2005)
Vandebril, R., Van Barel, M., Golub, G., Mastronardi, N.: A bibliography on semiseparable matrices. Calcolo 42(3), 249–270 (2005)
Vandebril, R., Van Barel, M., Mastronardi, N.: Matrix Computations and Semiseparable Matrices: Linear Systems, vol. 1. JHU Press (2007)
Wen, W., Wu, C., Wang, Y., Chen, Y., Li, H.: Learning structured sparsity in deep neural networks. In: Advances in Neural Information Processing Systems, pp. 2074–2082 (2016)
Xie, D., Xiong, J., Pu, S.: All you need is beyond a good init: exploring better solution for training extremely deep convolutional neural networks with orthonormality and modulation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6176–6185 (2017)
Zamarreño, J.M., Vega, P.: State space neural network. properties and application. Neural Netw. 11(6), 1099–1112 (1998)
Zhao, L., Liao, S., Wang, Y., Li, Z., Tang, J., Yuan, B.: Theoretical properties for neural networks with weight matrices of low displacement rank. In: Proceedings of the 34th International Conference on Machine Learning, vol. 70, pp. 4082–4090. JMLR. org (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Kissel, M., Gottwald, M., Gjeroska, B., Paukner, P., Diepold, K. (2022). Backpropagation Through States: Training Neural Networks with Sequentially Semiseparable Weight Matrices. In: Marreiros, G., Martins, B., Paiva, A., Ribeiro, B., Sardinha, A. (eds) Progress in Artificial Intelligence. EPIA 2022. Lecture Notes in Computer Science(), vol 13566. Springer, Cham. https://doi.org/10.1007/978-3-031-16474-3_39
Download citation
DOI: https://doi.org/10.1007/978-3-031-16474-3_39
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-16473-6
Online ISBN: 978-3-031-16474-3
eBook Packages: Computer ScienceComputer Science (R0)