Information and Communications Magazine (정보와 통신)

The Korean Institute of Commucations and Information Sciences (한국통신학회)
권호 표지

Deep Learning: 기계학습의 새로운 트랜드

  • Published : 2014.10.31
Download PDF
⟨ Previous Next ⟩

Abstract

Deep learning은 많은 수의 계층으로 이루어진 깊은 신경망을 학습하기 위한 연구 분야이다. 지난 수 년 동안 deep learning은 다양한 분야에 적용되어 기존 방법들을 능가하는 높은 성능을 보였으며, 그 결과 기계학습 및 패턴인식 분야에서 가장 중요한 기술적 트랜드가 되어가고 있다. 깊은 신경망의 장점과 그 동안 깊은 신경망의 학습이 어려웠던 이유를 설명하고 이러한 어려움을 극복한 새로운 알고리즘들을 소개한다. 마지막으로 deep learning의 성공적 응용 사례에 대해 소개한다.

Keywords

References

  1. Y. Bengio, Learning deep architectures for AI, Foundations and Trends in Machine Learning, vol. 2, iss. 1, pp. 1-127, 2009. https://doi.org/10.1561/2200000006
  2. G. E. Hinton, S. Osindero, Y. Teh, A fast learning algorithm for deep belief nets. Neural Computation vol. 18, no. 7, pp. 1527-1554, 2006. https://doi.org/10.1162/neco.2006.18.7.1527
  3. Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, Gradient-based learning applied to document recognition, Proceedings of the IEEE, vol. 86, no. 11, pp. 2278-2324, 1998. https://doi.org/10.1109/5.726791
  4. http://en.wikipedia.org/wiki/Multilayer_perceptron
  5. https://developer.nvidia.com/cuda-zone
  6. http://en.wikipedia.org/wiki/Backpropagation
  7. P. Vincent, H. Larochelle, Y. Bengio, and P.-A. Manzagol, Extracting and composing robust features with denoising autoencoders, in Proceedings of the Twenty-fifth International Conference on Machine Learning (ICML'08), (W. W. Cohen, A. McCallum, and S. T. Roweis, eds.), pp. 1096-1103, ACM, 2008.
  8. D. C. Cireşan, U. Meier, J. Schmidhuber. Multic olumn Deep Neural Networks for Image Classification. IEEE Conf. on Computer Vision and Pattern Recognition 2012.
  9. D. C. Cireşan and J. Schmidhuber. Multi-column Deep Neural Networks for Offline Handwritten Chinese Character Classification, IDSIA Technical Report No. IDSIA-05-13, 2013.
  10. K. Fukushima, Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biological Cybernetics, vol. 36, no. 4, pp. 193-202, 1980. https://doi.org/10.1007/BF00344251
  11. http://yann.lecun.com/exdb/mnist
  12. Cheng-Lin Liu, Fei Yin, Qiu-Feng Wang, Da-Han Wang, ICDAR 2011 Chinese Handwriting Recognition Competition, 2011. (http://www.nlpr.ia.ac.cn/events/HRcompetition/Report.html)
  13. Fei Yin, Qiu-Feng Wang, Xu-Yao Zhang, Cheng-Lin Liu, ICDAR 2013 Chinese Handwriting Recognition Competition, 2011. (http://www.nlpr.ia.ac.cn/events/CHRcompetition2013/competition/Report.html)
  14. http://www.image-net.org/challenges/LSVRC/2014/results
  15. Yaniv Taigman, Ming Yang, Marc'Aurelio Ranzato, Lior Wolf, DeepFace: Closing the Gap to Human-Level Performance in Face Verification, CVPR2013.
  16. Hinton, Geoffrey, et al. "Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups." Signal Processing Magazine, IEEE 29.6 (2012): 82-97.
  17. In-Jung Kim, Xiaohui Xie, Handwritten Hangul recognition using deep convolutional neural networks, International Journal on Document Analysis and Recognition (IJDAR) Sep. 2014. (http://link.springer.com/article/10.1007/s10032-014-0229-4)