Journal of the Korean Society of Mechanical Technology (한국기계기술학회지)

Korean Society of Mechanical Technology (한국기계기술학회)
권호 표지
DOI QR코드

DOI QR Code

Design of CNN with MLP Layer

MLP 층을 갖는 CNN의 설계

  • Park, Jin-Hyun (Mechatronics Eng., Gyeongnam Nat'l Univ. of Science and Technology) ;
  • Hwang, Kwang-Bok (Mechatronics Eng., Gyeongnam Nat'l Univ. of Science and Technology) ;
  • Choi, Young-Kiu (Dept. of Electrical Engineering, Pusan National University)
  • Received : 2018.10.11
  • Accepted : 2018.11.09
  • Published : 2018.12.28
⟨ Previous Next ⟩

Abstract

After CNN basic structure was introduced by LeCun in 1989, there has not been a major structure change except for more deep network until recently. The deep network enhances the expression power due to improve the abstraction ability of the network, and can learn complex problems by increasing non linearity. However, the learning of a deep network means that it has vanishing gradient or longer learning time. In this study, we proposes a CNN structure with MLP layer. The proposed CNNs are superior to the general CNN in their classification performance. It is confirmed that classification accuracy is high due to include MLP layer which improves non linearity by experiment. In order to increase the performance without making a deep network, it is confirmed that the performance is improved by increasing the non linearity of the network.

Keywords

References

  1. Guang Chen, Peng Sun, Yi Shang, "Automatic Fish Classification System Using Deep Learning," International Conference on Tools with Artificial Intelligence, IEEE computer society, 2017
  2. J. Cao, Y. Pang, and X. Li, "Pedestrian detection inspired by appearance constancy and shape symmetry," Proc. IEEE Int. Conf. Comput. Vis. Pattern Recognit., pp. 1316-1324, Sep. 2016
  3. Tae-Hwan Lee and Jin-Hyun Park, "Modelling for the Full Ranges of the Steam Table using Neural Networks," Journal of Korean Society of Mechanical Technology, Vol. 20, No. 1, pp. 82-88, 2018 https://doi.org/10.17958/ksmt.20.1.201802.82
  4. 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
  5. Y. Bengio, "Learning deep architectures for AI," Foundations and Trends in Machine Learning, Vol. 2, No. 1, pp. 1-127, 2009 https://doi.org/10.1561/2200000006
  6. 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
  7. Eon-Ho Lee and Se-Jin Lee, "Development of Modified Spherical Signature Descriptor Using 3D Point Cloud Data and Application to Convolutional Neural Network for Urban Structure Classification," Journal of Korean Society of Mechanical Technology, Vol. 20, No. 1, pp. 18-25, 2018 https://doi.org/10.17958/ksmt.20.1.201802.18
  8. Alex Krizhevsky, Ilya Sutskever, and Geoffrey E. Hinton, "Imagenet classification with deep convolutional neural networks," Advances in neural information processing systems, Vol. 25, pp. 1-9, 2012
  9. G. E. Hinton and R. R. Salakhutdinov, "Reducing the dimensionality of data with neural networks," Science, Vol. 313, pp. 504-507, 2006 https://doi.org/10.1126/science.1127647
  10. Min Lin, Qiang Chen, Shuicheng Yan, "Network in network," CoRR, vol. abs/1312.4400, 2013 [Online]. Available: http://arxiv.org/abs/1312.4400
  11. Yanwei Pang, Manli Sun, Xiaoheng Jiang, and Xuelong Li, "Convolution in Convolution for Network in Network," IEEE Trans. on Neural Networks and Learning Systems, Vol. 29, No. 5, May 2018
  12. https://kr.mathworks.com/help/deeplearning/ref/googlenet.html

Cited by

  1. Efficient Data Acquisition and CNN Design for Fish Species Classification in Inland Waters vol.18, pp.2, 2018, https://doi.org/10.6109/jicce.2020.18.2.106