An experimental evaluation of extreme learning machines on several hardware devices
- 17 Downloads
As an important learning algorithm, extreme learning machine (ELM) is known for its excellent learning speed. With the expansion of ELM’s applications in the field of classification and regression, the need for its real-time performance is increasing. Although the use of hardware acceleration is an obvious solution, how to select the appropriate acceleration hardware for ELM-based applications is a topic worthy of further discussion. For this purpose, we designed and evaluated the optimized ELM algorithms on three kinds of state-of-the-art acceleration hardware, i.e., multi-core CPU, Graphics Processing Unit (GPU), and Field-Programmable Gate Array (FPGA) which are all suitable for matrix multiplication optimization. The experimental results showed that the speedup ratio of these optimized algorithms on acceleration hardware achieved 10–800. Therefore, we suggest that (1) use GPU to accelerate ELM algorithms for large dataset, and (2) use FPGA for small dataset because of its lower power, especially for some embedded applications. We also opened our source code.
KeywordsExtreme learning machine Hardware Multi-core GPU FPGA
Gang Wu is supported by the NSFC (Grant No.61872072) and the State Key Laboratory of Computer Software New Technology Open Project Fund (Grant No.KFKT2018B05). Guoren Wang is the corresponding author of this paper. Guoren Wang is supported by the NSFC (Grant No. U1401256, 61732003, 61332006 and 61729201).
Compliance with ethical standards
Conflict of interest
The authors declared that they have no conflict of interest to this work.
- 1.Alia-Martinez M, Antoñanzas J, Antonanzas-Torres F, Pernía-Espinoza A, Urraca R (2015) A straightforward implementation of a gpu-accelerated ELM in R with NVIDIA graphic cards. In: International conference on hybrid artificial intelligence systems. Springer, Berlin, pp 656–667Google Scholar
- 3.Deng L, Yu D, et al (2014) Deep learning: methods and applications. Found Trends® Signal Process 7(3–4):197–387Google Scholar
- 6.Hagan MT, Demuth HB, Beale MH, De Jesús O (1996) Neural network design, vol 20. Pws Pub, BostonGoogle Scholar
- 13.Huang GB, Liang NY, Rong HJ, Saratchandran P, Sundararajan N (2005) On-line sequential extreme learning machine. Comput Intell 2005:232–237Google Scholar
- 17.Jeowicz T, Gajdo P, Uher V, Snáel V (2015) Classification with extreme learning machine on GPU. In: 2015 international conference on intelligent networking and collaborative systems (INCOS), pp 116–122. IEEEGoogle Scholar
- 18.Li H, Wu G (2014) Map matching for taxi GPS data with extreme learning machine. In: Advanced data mining and applications—10th international conference, ADMA 2014, Guilin, China, December 19–21, 2014. Proceedings, pp 447–460. https://doi.org/10.1007/978-3-319-14717-8_35
- 21.Liaw A, Wiener M et al (2002) Classification and regression by randomforest. R News 2(3):18–22Google Scholar
- 23.Magsi H, Sodhro AH, Chachar FA, Abro SAK, Sodhro GH, Pirbhulal S (2018) Evolution of 5g in internet of medical things. In: 2018 international conference on computing, mathematics and engineering technologies (iCoMET), pp 1–7. IEEEGoogle Scholar
- 25.Safaei A, Wu QJ, Yang Y, Akılan T (2017) System-on-a-chip (soc)-based hardware acceleration for extreme learning machine. In: 2017 24th IEEE international conference on electronics, circuits and systems (ICECS), pp 470–473. IEEEGoogle Scholar
- 29.Sodhro AH, Malokani AS, Sodhro GH, Muzammal M, Zongwei L (2019) An adaptive QOS computation for medical data processing in intelligent healthcare applications. Neural Comput Appl, pp 1–12Google Scholar
- 33.Sodhro AH, Shaikh FK, Pirbhulal S, Lodro MM, Shah MA (2017) Medical-QoS based telemedicine service selection using analytic hierarchy process. In: Handbook of large-scale distributed computing in smart healthcare. Springer, Berlin, pp 589–609Google Scholar
- 39.Woods L, Teubner J, Alonso G (2011) Real-time pattern matching with FPGAD. In: 2011 IEEE 27th international conference on data engineering (ICDE), pp 1292–1295. IEEEGoogle Scholar
- 40.Yeam TC, Ismail N, Mashiko K, Matsuzaki T (2017) FPGA implementation of extreme learning machine system for classification. In: Region 10 conference, TENCON 2017-2017 IEEE, pp 1868–1873. IEEEGoogle Scholar