Accelerating FCM neural network classifier using graphics processing units with CUDA
- 360 Downloads
With the advancement in experimental devices and approaches, scientific data can be collected more easily. Some of them are huge in size. The floating centroids method (FCM) has been proven to be a high performance neural network classifier. However, the FCM is difficult to learn from a large data set, which restricts its practical application. In this study, a parallel floating centroids method (PFCM) is proposed to speed up the FCM based on the Compute Unified Device Architecture, especially for a large data set. This method performs all stages as a batch in one block. Blocks and threads are responsible for evaluating classifiers and performing subtasks, respectively. Experimental results indicate that the speed and accuracy are improved by employing this novel approach.
KeywordsNeural networks classifier Parallel floating centroids method Compute unified device architecture Graphics processing units
This work was supported by National Key Technology Research and Development Program of the Ministry of Science and Technology under Grant 2012BAF12B07-3. National Natural Science Foundation of China under Grant Nos. 61173078, 61203105, 61173079, 61070130, 60903176. Provincial Natural Science Foundation for Outstanding Young Scholars of Shandong under Grant No. JQ200820. Shandong Provincial Natural Science Foundation, China, under Grant Nos. ZR2010FM047, ZR2012FQ016, ZR2012FM010. Program for New Century Excellent Talents in University under Grant No. NCET-10-0863.
- 4.Qinlan JR (1986) Introduction of decision trees. Mach Learn 1(1):86–106 Google Scholar
- 19.Zhang L, Wang L, Wang X, Liu K, Abraham A (2012) Research of neural network classifier based on FCM and PSO for breast cancer classification. In: HAIS 2012, part I. Lecture notes in computer science, vol 7208, pp 647–654 Google Scholar
- 20.Czarnowski I, Jedrzejowicz P (2012) Agent-based approach to RBF network training with floating centroids. In: The 4th international conference on computational collective intelligence, pp 453–462 Google Scholar
- 22.Srinivasan N, Vaidehi V (2005) Cluster computing for neural network based amomaly detection. In: 13th IEEE international conference on networks jointly held with the 7th IEEE Malaysia international conference on communications, pp 130–134 Google Scholar
- 25.Guorui Y, Jie T, Shouping Z et al (2008) Fast cone-beam CT image reconstruction using GPU hardware. J X-Ray Sci Technol 16(4):225–234 Google Scholar
- 29.Kennedy J, Eberhart RC (1995) A new optimizer using paritcle swarm theory. In: Proc. the sixth int. symposium on micromachine and human science, pp 39–43 Google Scholar
- 35.Fang W, Lau KK, Lu M, Xiao X, Lam CK, Yang PY, He B, Luo Q, Sande PV, Yang K (2008) Parallel Data Mining on Graphics Processors. Technical Report HKUSTCS08 Google Scholar