Parallel Implementation on FPGA of Support Vector Machines Using Stochastic Gradient Descent
Open accessAbstract
Sequential Minimal Optimization (SMO) is the traditional training algorithm for Support Vector Machines (SVMs). However, SMO does not scale well with the size of the training set. For that reason, Stochastic Gradient Descent (SGD) algorithms, which have better scalability, are a better option for massive data mining applications. Furthermore, even with the use of SGD, training times can become extremely large depending on the data set. For this reason, accelerators such as Field-programmable Gate Arrays (FPGAs) are used. This work describes an implementation in hardware, using FPGA, of a fully parallel SVM using Stochastic Gradient Descent. The proposed FPGA implementation of an SVM with SGD presents speedups of more than 10,000× relative to software implementations running on a quad-core processor and up to 319× compared to state-of-the-art FPGA implementations while requiring fewer hardware resources. The results show that the proposed architecture is a viable solution for highly demanding problems such as those present in big data analysis.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
A highly scalable and parameterizable FPGA-based Stochastic Gradient Descent (SGD) can be used for different applications such as linear model training, and SGD techniques achieve convergence quality with a slight tradeoff for algorithm precision (e.g., using fixed-point implementations).
“In terms of hardware efficiency, SGD techniques were able to achieve the convergence quality, with a slight tradeoff for the algorithm precision (e.g., using fixed-point implementations [7]).”
From Embedded Intelligence on FPGA: Survey, Applications and Challenges (2021) · cites this paper as [7]
Split into 2 atoms — 1 confirmed, 1 partially supported, 0 disputed, 0 misattributed, 0 unverifiable. Expand the claim to see per-atom verdicts.
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Scikit-learn: Machine Learning in Python
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Müller, A., Nothman, J., Louppe, G., et al. (2012) · arXiv · doi:10.48550/arxiv.1201.0490 · Cited by 71,016 · see citing works
Schölkopf, B., & Smola, A. J. (2001) · The MIT Press eBooks · doi:10.7551/mitpress/4175.001.0001 · Cited by 11,934 · see citing works
Neural Networks And Learning Machines
Haykin, S. (2010) · Cited by 6,611 · see citing works
(1998) · Cited by 2,679 · see citing works
Pegasos: primal estimated sub-gradient solver for SVM
Shalev‐Shwartz, S., Singer, Y., Srebro, N., & Cotter, A. (2010) · Mathematical Programming · doi:10.1007/s10107-010-0420-4 · Cited by 1,502 · see citing works
Demir-Kavuk, O., Kamada, M., Akutsu, T., & Knapp, E. (2011) · BMC Bioinformatics · doi:10.1186/1471-2105-12-412 · Cited by 134 · see citing works
Understanding and Optimizing Asynchronous Low-Precision Stochastic Gradient Descent
De, C., Feldman, M., Ré, C., & Olukotun, K. (2017) · Proceedings - International Symposium on Computer Architecture/Proceedings · doi:10.1145/3079856.3080248 · Cited by 104 · see citing works
Embedded Hardware-Efficient Real-Time Classification With Cascade Support Vector Machines
Kyrkou, C., Bouganis, C.-S., Theocharides, T., & Polycarpou, M. M. (2015) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2015.2428738 · Cited by 82 · see citing works
FPGA-Accelerated Dense Linear Machine Learning: A Precision-Convergence Trade-Off
Kara, K., Alistarh, D., Alonso, G., Mutlu, O., & Zhang, C. (2017) · 2017 IEEE 25th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM) · doi:10.1109/fccm.2017.39 · Cited by 77 · see citing works
Parallel Implementation of Reinforcement Learning Q-Learning Technique for FPGA
da Silva, L. M. D., Torquato, M. F., & Fernandes, M. A. C. (2018) · IEEE Access · doi:10.1109/access.2018.2885950 · Cited by 64 · see citing works
Self-citationA system on chip for melanoma detection using FPGA-based SVM classifier
Afifi, S. M., GholamHosseini, H., & Sinha, R. (2018) · Microprocessors and Microsystems · doi:10.1016/j.micpro.2018.12.005 · Cited by 64 · see citing works
SVM algorithm oriented for implementation in a low-cost Xilinx FPGA
Wiśniewski, R., Bazydło, G., & Szcześniak, P. (2018) · Integration · doi:10.1016/j.vlsi.2018.10.002 · Cited by 17 · see citing works
The Stochastic Gradient Descent for the Primal L1-SVM Optimization Revisited
Panagiotakopoulos, C., & Tsampouka, P. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-40994-3_5 · Cited by 9 · see citing works
Scalable Hardware Accelerator for Mini-Batch Gradient Descent
Rasoori, S., & Akella, V. (2018) · ACM Great Lakes Symposium on VLSI (GLSVLSI) · doi:10.1145/3194554.3194559 · Cited by 4 · see citing works
Towards FPGA-assisted spark: An SVM training acceleration case study
Ho, S. M. H., Wang, M., Ng, H.-C., & So, H. K. (2016) · International Conference on ReConFigurable Computing and FPGAs (ReConFig) · doi:10.1109/reconfig.2016.7857194 · Cited by 3 · see citing works
The Stochastic Gradient Descent for the Primal L1-SVM Optimization RevisitedPreprint
Panagiotakopoulos, C., & Tsampouka, P. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1304.6383 · Cited by 1 · see citing works
Flagged first, then by citations
1 of the 17 references couldn’t be matched to a known paper.
Research works printed but not linked: 1
- Wang, Z.; Crammer, K.; Vucetic, S. Breaking the curse of kernelization: Budgeted stochastic gradient descent for large-scale svm training. J. Mach. Learn. Res. 2012, 13, 3103-3131.
Cited by
Sorted by citations
Embedded Intelligence on FPGA: Survey, Applications and Challenges
Seng, K. P., Lee, P. J., & Ang, L. M. (2021) · Electronics · doi:10.3390/electronics10080895 · Cited by 105 · see citing works
Alimisis, V., Gennis, G., Gourdouparis, M., Dimas, C., & Sotiriadis, P. P. (2023) · Sensors · doi:10.3390/s23083978 · Cited by 57 · see citing works
Ramadurgam, S., & Perera, D. G. (2021) · Electronics · doi:10.3390/electronics10111323 · Cited by 29 · see citing works
An FPGA-Based Neuro-Fuzzy Sensor for Personalized Driving Assistance
Mata-Carballeira, Ó., Gutiérrez‐Zaballa, J., del Campo, I., & Martinez, V. S. (2019) · Sensors · doi:10.3390/s19184011 · Cited by 23 · see citing works
Classification Model on Big Data in Medical Diagnosis Based on Semi-Supervised Learning
Wang, L., Qian, Q., Zhang, Q., Wang, J., Cheng, W., & Yan, W. Q. (2020) · The Computer Journal · doi:10.1093/comjnl/bxaa006 · Cited by 22 · see citing works
FPGA implementation of breast cancer detection using SVM linear classifier
Laxmisagar, H. S., & Hanumantharaju, M. C. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-15121-6 · Cited by 20 · see citing works
Direct symbol decoding using GA-SVM in chaotic baseband wireless communication system
Yin, H., & Ren, H. (2021) · Journal of the Franklin Institute · doi:10.1016/j.jfranklin.2021.06.012 · Cited by 20 · see citing works
Nonintrusive Load Monitoring Based on Complementary Features of Spurious Emissions
Su, D., Shi, Q., Xu, H., & Wang, W. (2019) · Electronics · doi:10.3390/electronics8091002 · Cited by 17 · see citing works
FPGA-Based Implementation of Stochastic Configuration Networks for Regression Prediction
Gao, Y., Luan, F., Pan, J., Li, X., & He, Y. (2020) · Sensors · doi:10.3390/s20154191 · Cited by 16 · see citing works
Mahdi, G. J. M. (2020) · Baghdad Science Journal · doi:10.21123/bsj.2020.17.4.1255 · Cited by 15 · see citing works
Hardware Architecture Proposal for TEDA Algorithm to Data Streaming Anomaly Detection
Silva, L. M. D. D., Coutinho, M. G. F., Santos, C. E. B., Santos, M. R., Ruiz, M. D., Guedes, L. A., & Fernandes, M. A. C. (2021) · IEEE Access · doi:10.1109/access.2021.3098004 · Cited by 14 · see citing works
Self-citationAn efficient algorithm for data parallelism based on stochastic optimization
Alnowibet, K. A., Khan, I., Sallam, K. M., & Mohamed, A. W. (2022) · Alexandria Engineering Journal · doi:10.1016/j.aej.2022.05.052 · Cited by 12 · see citing works
Proposal of Takagi–Sugeno Fuzzy-PI Controller Hardware
Silva, S. N., Lopes, F. F., Valderrama, C. A., & Fernandes, M. A. C. (2020) · Sensors · doi:10.3390/s20071996 · Cited by 11 · see citing works
Self-citationFPGA Applied to Latency Reduction for the Tactile Internet
José, C. V. S., Silva, S. N., Torquato, M. F., Mahmoodi, T., Döhler, M., & Fernandes, M. A. C. (2022) · Sensors · doi:10.3390/s22207851 · Cited by 9 · see citing works
Self-citationDhavlle, A., & Dinakarrao, S. M. P. (2020) · International Green and Sustainable Computing Conference · doi:10.1109/igsc51522.2020.9291173 · Cited by 5 · see citing works
Improved Image-Based Welding Status Recognition with Dimensionality Reduction and Shallow Learning
Ferreira, G. R. B., & Ayala, H. V. H. (2022) · Experimental Mechanics · doi:10.1007/s11340-022-00850-w · Cited by 4 · see citing works
Deep Learning Correction Algorithm for The Active Optics System
Li, W., Chao, K., Guan, H., Huang, S., Zhao, J., Zhou, X., & Li, J. (2020) · Sensors · doi:10.3390/s20216403 · Cited by 4 · see citing works
Wang, J., Zhang, B., & Shu, L. (2023) · Electronics · doi:10.3390/electronics12143138 · Cited by 4 · see citing works
Non-linear support vector machine classification models using kernel tricks with applications
Mohammed, S. F., & Mahdi, G. J. M. (2024) · AIP conference proceedings · doi:10.1063/5.0196147 · Cited by 3 · see citing works
Fully Parallel Proposal of Naive Bayes on FPGA
Barros, W. K. P., Barbosa, M. T. M., Dias, L. A., & Fernandes, M. A. C. (2022) · Electronics · doi:10.3390/electronics11162565 · Cited by 3 · see citing works
Self-citationPrediction Techniques on FPGA for Latency Reduction on Tactile Internet
Silva, S. N., da Silva, L. M. D., Dias, L. A., & Fernandes, M. A. C. (2022) · Sensors · doi:10.3390/s22093556 · Cited by 2 · see citing works
Self-citationResearch and Implementation of ε-SVR Training Method Based on FPGA
Wu, R., Liu, B., Fu, J., Xu, M., Fu, P., & Li, J. (2019) · Electronics · doi:10.3390/electronics8090919 · Cited by 2 · see citing works
Mohsin, M. A., & Perera, D. G. (2025) · IEEE Access · doi:10.1109/access.2025.3645763 · Cited by 1 · see citing works
Ramadurgam, S. (2021) · Digital Collections of Colorado (Colorado State University) · Cited by 1 · see citing works
A high-performance FPGA architecture for Acceleration of SVM Machine Learning Training
Kardaris, C., Kachris, C., & Soudris, D. (2022) · Panhellenic Conference on Electronics & Telecommunications (PACET) · doi:10.1109/pacet56979.2022.9976358 · Cited by 1 · see citing works
Proposta de Implementação em Hardware de SVM multi-kernel para Aplicações em IoT
Filho, L. F. C., Coutinho, M. G. F., & Fernandes, M. A. C. (2021) · Anais do ... Simpósio Brasileiro de Automação Inteligente/Simpósio Brasileiro de Automação Inteligente · doi:10.20906/sbai.v1i1.2764
Self-citationA comparative study of gradient descent and stochastic gradient descent method for optimization
Shrimali, S., Sharma, G. S., & Srivastava, S. K. (2023) · AIP conference proceedings · doi:10.1063/5.0148736
Shrivastava, S., Kaur, A., & Singh, G. (2024) · Asian Conference on Intelligent Technologies (ACOIT) · doi:10.1109/acoit62457.2024.10939522
Point-of-Care Breast Cancer-on-Chip Diagnosis Using Linear SVM Model
Bhowmik, T., Gupta, D., Sharma, A., Rajput, A. K., Sanki, P. K., Pattnaik, M., & Jana, B. (2025) · IEEE India Conference · doi:10.1109/indicon68490.2025.11393007
- Authors
- Lopes, F. F., Ferreira, J. C., & Fernandes, M. A. C.
- Affiliations
- Universidade Federal do Rio Grande do Norte (BR)
- Universidade do Porto (PT)
- Corresponding author
- Fernandes, Marcelo A. C.
- Venue
- Electronics
- Publisher
- MDPI AG
- Published
- 2019-06-05
- Volume
- 8
- Issue
- 6
- Pages
- 631
- ISSN
- 2079-9292 (ISSN-L)
- OpenAlex
- W2948458866
- Cited by
- 29
- References
- 17
- Citations by year
- 2025: 2 · 2024: 2 · 2023: 4 · 2022: 6 · 2021: 6 · 2020: 6 · 2019: 3
- FWCI
- 5.33
- Type
- journal article
- Language
- en
- Open access
- gold
- dx.doi.org
- Licence
- Locations
- Electronics (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (Finance Code 001)
- Topics
- Physical Sciences › Computer Science › Hardware and Architecture › Embedded Systems Design Techniques
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Embedded Systems and FPGA Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and ELM
- Keywords
- support vector machine, stochastic gradient descent, FPGA implementation, parallel hardware architecture, big data mining, hardware resource efficiency, scalability
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
