Publicado

2023-05-25

Support vector machines implementation over integers modulo-M and Residue Number System

Implementación de máquinas de vectores de soporte sobre enteros módulo-M y en el Sistema Numérico de los Residuos

DOI:

https://doi.org/10.15446/dyna.v90n226.107112

Palabras clave:

modular arithmetic; pattern recognition; Residue Number System (RNS); Support Vector Machines (SVN); digital signal processing; radial basis function (en)
aritmética modular; reconocimiento de patrones; Sistema Numérico de los Residuos (SNR); Máquinas de Vectores de Soporte (MVS); procesamiento digital de señales; funciones de base radial (es)

Descargas

Autores/as

In low-power hardware implementations for classification algorithms, it is often essential to use physical resources efficiently. In this sense, the use of modulo-M integer operations instead of floating-point arithmetic, can lead to better performance, especially when M represents the dynamic range of an arithmetic block of the Residue Number System (RNS) [1,2]. Following this premise, this work is aiming to provide a methodology for implementing a classifier, specifically a Support Vector Machine (SVM) [3], using modulo-M integers and proposing a method for the use of Residue Number System.

En las implementaciones en hardware de baja potencia para algoritmos de clasificación, a menudo es esencial utilizar los recursos físicos de manera eficiente. En este sentido, la utilización de operaciones con enteros módulo-M en lugar de aritmética de punto flotante puede conducir a un mejor rendimiento, especialmente cuando M representa el rango dinámico de un bloque aritmético del Sistema Numérico de los Residuos (RNS) [1,2]. Siguiendo esta premisa, el objetivo de este trabajo es proporcionar una metodología para implementar un clasificador, en concreto, una Máquina de Vectores de Soporte (SVM) [3], utilizando enteros módulo-M y proponer un método para la utilización del Sistema Número de Residuos.

Descargas

Los datos de descargas todavía no están disponibles.

Citas

Cardarilli, G.C., Nannarelli, A. and Re, M., Residue number system for low-power DSP applications, in: 2007 Conference Record of the Forty-First Asilomar Conference on Signals, Systems and Computers, 2007, pp. 1412-1416. DOI: https://doi.org/10.1109/ACSSC.2007.4487461

Albicocco, P., Cardarilli, G. C., Nannarelli A. and Re, M., Twenty years of research on RNS for DSP: Lessons learned and future perspectives, 2014 International Symposium on Integrated Circuits (ISIC), pp. 436-439, 2014. DOI: https://doi.org/10.1109/ISICIR.2014.7029575

Boser, B.E., Guyon, I.M. and Vapnik, V.N., A training algorithm for optimal margin classifiers, in: Proceedings of the fifth annual workshop on Computational learning theory, 1992, pp. 144-152.

Cortes, C. and Vapnik, V., Support-vector networks, Machine learning, 1995, pp. 273-297.

Chang, C.H., Molahosseini, A.S., Zarandi, A.A.E. and Tay, T.F., Residue number systems: a new paradigm to datapath optimization for low-power and high-performance digital signal processing applications., IEEE Circuits and Systems Magazine, 15, pp. 26-44, 2015. DOI: https://doi.org/10.1109/MCAS.2015.2484118

Arthireena, S. and Shanmugavadivel, G., Efficient sign detection using parallel prefix adder, in: IEEE International Conference on Electrical, Instrumentation and Communication Engineering (ICEICE), 2017, pp. 1-5. DOI: https://doi.org/10.1109/ICEICE.2017.8191852

Hakonen, M., Piitulainen, H. and Visala, A., Current state of digital signal processing in myoelectric interfaces and related applications, Biomedical Signal Processing and Control, 18, pp. 334-359, 2015. DOI: https://doi.org/10.1016/j.bspc.2015.02.009

Liao, L.Z., Tseng, Y.L., Chiang, H.H. and Wang, W.Y., EMG-based control scheme with SVM classifier for assistive robot arm, in: 2018 International Automatic Control Conference, 2018, pp. 1-5. DOI: https://doi.org/10.1109/CACS.2018.8606762

Tymchyshyn, V. and Khlevniuk A., Yet more simple SMO algorithm, 2020.

Shashua, A., Introduction to machine learning: class notes, in Introduction to machine learning: class notes, 2009, pp. 30-39.

Jenkins, W.K., Soderstrand, M.A. and Radhakrishnan, C., Historical patterns of emerging residue number system technologies during the evolution of computer engineering and digital signal processing, in: IEEE International Symposium on Circuits and Systems (ISCAS), pp. 2018, pp. 1-5. DOI: https://doi.org/10.1109/ISCAS.2018.8351066

Shoup, V., Congruences, in a computational introduction to number theory and algebra, Cambridge University Press, U.K., 2009, 15 P. DOI: https://doi.org/10.1017/CBO9781139165464

Salamat, S., Imani, M., Gupta, S. and Rosing, T., Rnsnet: in-memory neural network acceleration using residue number system, in: 2018 IEEE International Conference on Rebooting Computing (ICRC), 2018, pp. 1-12. DOI: https://doi.org/10.1109/ICRC.2018.8638592

Chervyakov, N.I., Lyakhov, P.A., Deryabin, M.A., Nagornov, N.N., Valueva, M.V. and Valuev, G.V., Residue number system-based solution for reducing the hardware cost of a convolutional neural network, Neurocomputing, 407, pp. 439-453, 2020.

Roohi, A., Taheri, M., Angizi, S. and Fan, D., Rnsim: efficient deep neural network accelerator using residue number systems. In: 2021 IEEE/ACM International Conference on Computer Aided Design, ICCAD, 2021, pp. 1-9, DOI: https://doi.org/10.1016/j.neucom.2020.04.018

Roohi, A., Angizi, S., Navaeilavasani, P, and Taheri, M., ReFACE: efficient design methodology for acceleration of digital filter implementations, in: 2022 23rd International Symposium on Quality Electronic Design (ISQED), 2022, pp. 1-6. DOI: https://doi.org/10.1109/ISQED54688.2022.9806144

Givaki, K., Khonsari, A., Gholamrezaei, M.H., Gorgin, S. and Najafi, M.H., A generalized residue number system design approach for ultra-low power arithmetic circuits based on deterministic bit-streams, in: IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2023, 14 P. DOI: https://doi.org/10.1109/TCAD.2023.3250603

Ramírez, J., García, A., Meyer-Bäse, U., Taylor F. and Lloris, A., Implementation of RNS-based distributed arithmetic discrete wavelet transform architectures using field-programmable logic., Journal of VLSI Signal Processing Systems for Signal, Image and Video Technology, 33(1), pp. 171-190, 2003. [19] Nakahara, H. and Sasao, T., A deep convolutional neural network based on nested residue number system, in: 2015 25th International Conference on Field Programmable Logic and Applications (FPL), 2015, pp. 1-6. DOI: https://doi.org/10.1109/FPL.2015.7293933

Xu, W., You, X. and Zhang, C., Using Fermat number transform to accelerate convolutional neural network, in: 2017 IEEE 12th International Conference on ASIC (ASICON), 2017, pp. 1033-1036. DOI: https://doi.org/10.1109/ASICON.2017.8252655

Park, K.H. and Lee, S.W., Movement intention decoding based on deep learning for multiuser myoelectric interfaces, in: 2016 4th international winter conference on brain-computer Interface (BCI), 2016, pp. 1-2. DOI: https://doi.org/10.1109/IWW-BCI.2016.7457459

Lin, L.Y., Schroff, J., Lin, T P. and Huang, T.C., Residue number system design automation for neural network acceleration, in: IEEE International Conference on Consumer Electronics-Taiwan (ICCE-Taiwan), 2020, pp. 1-2. DOI: https://doi.org/10.1109/ICCE-Taiwan49838.2020.9258020

Sakellariou, V., Paliourasy, V., Kouretasy, I., Saleh, H. and Stouraitis, T., A High-performance RNS LSTM block, in: IEEE International Symposium on Circuits and Systems (ISCAS), 2022, pp. 1264-1268. DOI: https://doi.org/10.1109/ISCAS48785.2022.9937633

Sousa, L., Nonconventional computer arithmetic circuits, systems and applications, IEEE Circuits and Systems Magazine, 21(1), pp. 6-40, 2021. DOI: https://doi.org/10.1109/MCAS.2020.3027425

Samimi, N., Kamal, M., Afzali-Kusha, A. and Pedram, M., Res-DNN: a residue number system-based DNN accelerator unit., IEEE Transactions on Circuits and Systems I: regular papers, 67(2), pp. 658-671, 2019. DOI: https://doi.org/10.1109/TCSI.2019.2951083

Soloviev, R., Telpukhov, D., Mkrtchan, I., Kustov, A. and Stempkovskiy, A., Hardware implementation of convolutional neural networks based on residue number system, in: Moscow Workshop on Electronic and Networking Technologies (MWENT), 2020, pp. 1-7. DOI: https://doi.org/10.1109/MWENT47943.2020.9067498

Ran, S., Zhao, B., Dai, X., Cheng, C. and Zhang,Y., Software-hardware co-design for accelerating large-scale graph convolutional network inference on FPGA., Neurocomputing, 532, pp. 129-140, 2023. DOI: https://doi.org/10.1016/j.neucom.2023.02.032.

Licencia

Derechos de autor 2023 DYNA

Creative Commons License

Esta obra está bajo una licencia internacional Creative Commons Atribución-NoComercial-SinDerivadas 4.0.

El autor o autores de un artículo aceptado para publicación en cualquiera de las revistas editadas por la facultad de Minas cederán la totalidad de los derechos patrimoniales a la Universidad Nacional de Colombia de manera gratuita, dentro de los cuáles se incluyen: el derecho a editar, publicar, reproducir y distribuir tanto en medios impresos como digitales, además de incluir en artículo en índices internacionales y/o bases de datos, de igual manera, se faculta a la editorial para utilizar las imágenes, tablas y/o cualquier material gráfico presentado en el artículo para el diseño de carátulas o posters de la misma revista.