한국전자통신학회논문지 (The Journal of the Korea institute of electronic communication sciences)

한국전자통신학회 (Korea Institute of Electronic Communication Science)
권호 표지
DOI QR코드

DOI QR Code

딥 러닝 프레임워크의 비교 및 분석

A Comparison and Analysis of Deep Learning Framework

  • 투고 : 2016.10.26
  • 심사 : 2017.02.24
  • 발행 : 2017.02.28
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

딥 러닝은 사람이 가르치지 않아도 컴퓨터가 스스로 사람처럼 학습할 수 있는 인공지능 기술이다. 딥 러닝은 세상을 이해하고 감지하는 인공지능을 개발하는데 가장 촉망받는 기술이 되고 있으며, 구글, 바이두, 페이스북 등이 가장 앞서서 개발을 하고 있다. 본 논문에서는 딥 러닝을 구현하는 딥 러닝 프레임워크의 종류에 대해 논의하고, 딥 러닝 프레임워크의 영상과 음성 인식 분야의 효율성에 대해 비교, 분석하고자 한다.

Deep learning is artificial intelligence technology that can teach people like themselves who need machine learning. Deep learning has become of the most promising in the development of artificial intelligence to understand the world and detection technology, and Google, Baidu and Facebook is the most developed in advance. In this paper, we discuss the kind of deep learning frameworks, compare and analyze the efficiency of the image and speech recognition field of it.

키워드

참고문헌

  1. Y. LeCun, Y. Bengio, and G. Hinton. "Deep learning," Nature, vol. 521, no. 7553, 2015, pp. 436-444. https://doi.org/10.1038/nature14539
  2. J. Schmidhuber, "Deep Learning in Neural Networks: An Overview," Neural Networks, vol. 61, Jan. 2015, pp. 85-117. https://doi.org/10.1016/j.neunet.2014.09.003
  3. J. Choi, "Speech and Noise Recognition System by Neural Network," J. of the Korea Institute of Electronic Communication Sciences, vol. 5, no. 4, 2010, pp. 357-362.
  4. J. Cho and H. Yang, "A Car License Plate Recognition Using Colors Information, Morphological Characteristic and Neural Network," J. of the Korea Institute of Electronic Communication Sciences, vol. 5, no. 3, 2010, pp. 304-308.
  5. J. Lee and J. Kim, "Recognition of a New Car Plate using Color Information and Error Back-propagation Neural Network Algorithms," J. of the Korea Institute of Electronic Communication Sciences, vol. 5, no. 5, 2010, pp. 471-476.
  6. Y. Jia, "Caffe: Convolutional Architecture for Fast Feature Embedding," Proc. MM '14 Proc. of the 22nd ACM Int. Conf. on Multimedia, Orlando, USA, November 03-07, 2014, pp. 675-678.
  7. F. Seide and A. Agarwal, "CNTK: Microsoft's Open-Source Deep-Learning Toolkit," KDD '16: Proc. of the 22nd ACM Special Interest Group (SIG) on Knowledge Discovery and Data Mining Int. Conf. on Knowledge Discovery and Data Mining, San francisco, USA, Aug. 2016, pp. 2135-2135.
  8. M. Abadi, "TensorFlow: learning functions at scale," ICFP 2016: Proc. of the 21st ACM Special Interest Group on programming languages Int. Conf. on Functional Programming, Nara, Japan, September 18-24, 2016.
  9. F. Bastien, P. Lamblin, R. Pascanu, J. Bergstra, I. Goodfellow, A. Bergeron, N. Bouchard, D. Warde-Farley, and Y. Bengio, "Theano: new features and speed improvements," Workshop on Deep Learning and Unsupervised Feature Learning at Neural Information Processing Systems, Lake Tahoe, USA, December 03-08, 2012.
  10. S. Tokui, K. Oono, S. Hido and J. Clayton. "Chainer: a next-generation open source framework for deep learning," In Workshop on Machine Learning Systems at Neural Information Processing Systems, Montreal, Canada, December 07-12, 2015.
  11. Y. Lee and P. Moon, "An Analysis of Deep Learning Toolkits Technology Trends," 2016 Conf. of the Korea Institute of Electronic Communication Sciences, Youngju, Korea, vol. 10, no. 2, June 03-04, 2016, pp. 522-525.