DOI QR코드

DOI QR Code

CNN의 컨볼루션 레이어, 커널과 정확도의 연관관계 분석

Association Analysis of Convolution Layer, Kernel and Accuracy in CNN

  • 공준배 (군산대학교) ;
  • 장민석 (군산대학교 컴퓨터정보통신공학부)
  • Kong, Jun-Bea ;
  • Jang, Min-Seok (School of Computer & Information & Communication Engineering, College of Engineering, Kunsan National University)
  • 투고 : 2019.09.11
  • 심사 : 2019.12.15
  • 발행 : 2019.12.31

초록

본 논문에서는 CNN의 컨볼루션 레이어 개수 및 커널의 크기와 개수가 CNN에 어떠한 영향을 끼치는지 실험을 통해 알아보기 위해 진행하였다. 또한 분석을 위해 일반적인 CNN도 실험하여 실험에 사용된 CNN과 비교하였다. 분석에 사용될 신경망들은 CNN을 기반으로 하며 각각의 실험모델들은 레이어 개수, 커널의 크기 및 개수를 일정한 값으로 고정해 실험을 진행하였다. 모든 실험에는 2계층의 완전연결계층을 고정으로 사용하였다. 다른 변수들은 모두 동일한 값을 주어 실험하였다. 분석결과 레이어의 수가 작을 경우 커널의 크기 및 개수와 상관없이 데이터의 분산 값이 작아 견고한 정확도를 보여주었다. 레이어의 수가 커질수록 정확도도 증가됐으나 일정 수치 이상부턴 오히려 정확도가 내려갔으며 분산 값도 커져 정확도 편차가 크게 나타났다. 커널의 개수는 다른 변수보다 학습속도에 큰 영향을 끼쳤다.

In this paper, we experimented to find out how the number of convolution layers, the size, and the number of kernels affect the CNN. In addition, the general CNN was also tested for analysis and compared with the CNN used in the experiment. The neural networks used for the analysis are based on CNN, and each experimental model is experimented with the number of layers, the size, and the number of kernels at a constant value. All experiments were conducted using two layers of fully connected layers as a fixed. All other variables were tested with the same value. As the result of the analysis, when the number of layers is small, the data variance value is small regardless of the size and number of kernels, showing a solid accuracy. As the number of layers increases, the accuracy increases, but from above a certain number, the accuracy decreases, and the variance value also increases, resulting in a large accuracy deviation. The number of kernels had a greater effect on learning speed than other variables.

키워드

참고문헌

  1. S. Chung and Y. Chung "Comparison of Audio Event Detection Performance using DNN," J. of the Korea Institute of Electronic Communication Sciences, vol. 13, no. 3, June 2018, pp. 571-578. https://doi.org/10.13067/JKIECS.2018.13.3.571
  2. A. Krizhevsky, I. Sutskever, and G. Hinton, "Imagenet classification with deep convolution al neural networks," Neural Information Processing Systems, South Lake Tahoe, USA, 2012.
  3. K. Simonyan and A. Zisserman, "Very deep convolutional networks for large-scale image recognition," The International Conference on Learning Representations, San Diego, USA, 2015.
  4. M. Zeiler and R. Fergus. "Visualizing and understanding convolutional neural networks," European Conference on Computer Vision, vol. 13, no. 1, Sept. 2014, pp. 818-833.
  5. C. Szegedy, W. Lium, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich, "Going deeper with convolutions," Computer Vision and Pattern Recognition, Boston, USA, 2015.
  6. K. He, X. Zhang, S. Ren, and J. Sun, "Deep Residual Learning for Image Recognition," Computer Vision and Pattern Recognition, Las Vegas, USA, 2016.
  7. G. Huang, Z. Liu, K. Weinberger, and L. Maaten, "Densely connected convolutional networks," Computer Vision and Pattern Recognition, Honolulu, USA, 2017.
  8. X. Zhang, X. Zhou, M. Lin, and J. Sun. "Shufflenet: An extremely efficient convolutional neural network for mobile devices," Computer Vision and Pattern Recognition, Salt Lake City, USA, 2018.
  9. G. Son and J. Park "A Study of Kernel Characteristics of CNN Deep Learning for Effective Fire Detection Based on Video," J. of the Korea Institute of Electronic Communication Sciences, vol. 13, no. 6, Dec. 2018, pp. 1257-1262. https://doi.org/10.13067/JKIECS.2018.13.6.1257
  10. J. Kong, H. Jang, M. Jang, and Y. Lee, "Analysis of CNN Performance According to various parameters," Information and Control Symp., Kunsan, Korea, 2019.
  11. S. Chung and Y. Chung "Sound Event Detection based on Deep Neural Networks," J. of the Korea Institute of Electronic Communication Sciences, vol. 14, no. 2, Apr. 2019, pp. 571-578.