International Journal of Advanced Culture Technology

  • 제5권2호
  • /
  • Pages.82-89
  • /
  • 2017
  • /
  • 2288-7202(pISSN)
  • /
  • 2288-7318(eISSN)
국제문화기술진흥원 (The International Promotion Agency of Culture Technology)
권호 표지
DOI QR코드

DOI QR Code

Influence on overfitting and reliability due to change in training data

  • 투고 : 2017.03.26
  • 심사 : 2017.04.28
  • 발행 : 2017.06.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

The range of problems that can be handled by the activation of big data and the development of hardware has been rapidly expanded and machine learning such as deep learning has become a very versatile technology. In this paper, mnist data set is used as experimental data, and the Cross Entropy function is used as a loss model for evaluating the efficiency of machine learning, and the value of the loss function in the steepest descent method is We applied the GradientDescentOptimize algorithm to minimize and updated weight and bias via backpropagation. In this way we analyze optimal reliability value corresponding to the number of exercises and optimal reliability value without overfitting. And comparing the overfitting time according to the number of data changes based on the number of training times, when the training frequency was 1110 times, we obtained the result of 92%, which is the optimal reliability value without overfitting.

키워드

참고문헌

  1. Moon Sung Eun,Jang Soo berm,Lee Jong Seock (2016,9)"Machine Learning and Deep Learning Technology Trends," Journal of the Korean Institute of Communication Sciences, Vol.33 No. 10, 49-56 (8 pages)
  2. Kim he min(2016.4), "Knowledge of Vitamin B1: Deep Learning in Alpha Go", KB Knowledge Vitamin, 16-31, 1-2 (2 pages)
  3. Kim JinKyung, Kim YoungHoon, Lee MoonSik,Ahn Jae-min (2017.1), "BPSK Performance Analysis Using Tensor Flow," Proceedings of the Korean Institute of Communication Sciences Conference,339-340(2page)
  4. Saitokoki "Deep running starting from the bottom", Hanbit Media (2017), p113-p115
  5. KimKyoungjae, "Data Mining using Instance Selection in Artificial Neural Networks for Bankruptcy Prediction" Korea Intelligent Information Systems Society 2004.6. 111-120 (10page)
  6. KimJuWoong, Kwon Jung Kwon,Eum Ki-Hwan, "Automatic Learning Algorithm for Performance Improvement of Backpropagation Algorithm", IEICE 2002.7.19.-27 (9pages)
  7. KoJinwook , Lee Chulsoo, "Performance Improvement of Neural Network Decision Boundary Feature Extraction Algorithm by Analytical Computation of Decision Boundary Vertical Vector", IEICE 2002, 4,
  8. Ansungman, Deep Learning Model and Its Applications, Korea Intelligent Information Systems Society
  9. Fukushima, K., "Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position," Biological Cybernetics, vol.36, no.4(1980), 193-202. https://doi.org/10.1007/BF00344251
  10. Salakhutdinov, R. and Hinton, G., "Deep Boltzmann machines," Proc. International Conference on Artificial Intelligence and Statistics, 2009, 448-455.
  11. Kim Jongyoung, "Introduction to Google TensorFLow" Korea Computer Information Journal, December 15, 2015 (7pages)