The Journal of the Convergence on Culture Technology (문화기술의 융합)

The International Promotion Agency of Culture Technology (국제문화기술진흥원)
권호 표지
DOI QR코드

DOI QR Code

A Method for accelerating training of Convolutional Neural Network

합성곱 신경망의 학습 가속화를 위한 방법

  • 최세진 (서경대학교 컴퓨터공학과) ;
  • 정준모 (서경대학교 전자공학과)
  • Received : 2017.09.13
  • Accepted : 2017.10.10
  • Published : 2017.11.30
Download PDF
⟨ Previous Next ⟩

Abstract

Recently, Training of the convolutional neural network (CNN) entails many iterative computations. Therefore, a method of accelerating the training speed through parallel processing using the hardware specifications of GPGPU is actively researched. In this paper, the operations of the feature extraction unit and the classification unit are divided into blocks and threads of GPGPU and processed in parallel. Convolution and Pooling operations of the feature extraction unit are processed in parallel at once without sequentially processing. As a result, proposed method improved the training time about 314%.

최근 CNN(Convolutional Neural Network)의 구조가 복잡해지고 신견망의 깊이가 깊어지고 있다. 이에 따라 신경망의 학습에 요구되는 연산량 및 학습 시간이 증가하게 되었다. 최근 GPGPU 및 FPGA를 이용하여 신경망의 학습 속도를 가속화 하는 방법에 대한 연구가 활발히 진행되고 있다. 본 논문에서는 NVIDIA GPGPU를 제어하는 CUDA를 이용하여 CNN의 특징추출부와 분류부에 대한 연산을 가속화하는 방법을 제시한다. 특징추출부와 분류부에 대한 연산을 GPGPU의 블록 및 스레드로 할당하여 병렬로 처리하였다. 본 논문에서 제안하는 방법과 기존 CPU를 이용하여 CNN을 학습하여 학습 속도를 비교하였다. MNIST 데이터세트에 대하여 총 5 epoch을 학습한 결과 제안하는 방법이 CPU를 이용하여 학습한 방법에 비하여 약 314% 정도 학습 속도가 향상된 것을 확인하였다.

Keywords

References

  1. G. Eason, B. Nobel, and I.N. Sneddon, "On certain integrals of Lipschitz-Hankel type involving products of Bessel functions", Phil. Trans. Roy. Soc. London, vol. A247, pp. 529-551, April 1955.
  2. J. Clerk Maxwell, A Treatise on Electricity and Magnetism, 3rd ed., vol. 2. Oxford: Clarendon, 1892, pp.68-73.
  3. I.S. Jacobs and C.P. Bean, "Fine particles, thin films and exchange anisotropy," in Magnetism, vol. III, G.T. Rado and H. Suhl, Eds. New York: Academic, 1963, pp. 271-350.
  4. K. Elissa, "Title of paper if known," unpublished
  5. R. Nicole, "Title of paper with only first word capitalized," J. Name Stand. Abbrev., in press.
  6. Y. Yorozu, M. Hirano, K. Oka, and Y. Tagawa, "Electron spectroscopy studies on magneto-optical media and plastic substrate interface," IEEE Transl. J. Magn. Japan, vol. 2, pp. 740-741, August 1987 [Digests 9th Annual Conf. Magnetics Japan, p. 301, 1982]. https://doi.org/10.1109/TJMJ.1987.4549593
  7. M. Young, The Technical Writer's Handbook. Mill Valley, CA: University Science, 1989.
  8. NVIDIA Corporations, CUDA C Programming GUIDE, January, 2017
  9. LeCun, Yann, and Yoshua Bengio. "Convolutional networks for images, speech, and time series." The handbook of brain theory and neural networks 3361, no.10 1995
  10. Nan-Ying Liang, Guang-Bin Huang, "A Fast and Accurate Online Sequential Learning Algorithm for Feedforward Networks," IEEE Transaction on Neural Networks, Vol. 17, Issue 6, pp. 1411-1423, Nov. 2016 https://doi.org/10.1109/TNN.2006.880583
  11. Rongqiang Qian, Zhao Wang, Frans Coenen, "Robust Chinese Traffic Sign Detection and Recognition with Deep Convolutional Neural Network," 2015 11th International Conference on Natural Computation(ICNC), 791-796, 2015.