Detailed Information
Cited 0 time in 
Cited 0 time in 
Cited 0 time in
Metadata Downloads
MLP 층을 갖는 CNN의 설계open accessDesign of CNN with MLP Layer
- Other Titles
- Design of CNN with MLP Layer
- Issue Date
- 2018
- Publisher
- 한국기계기술학회
- Keywords
- CNN(Convolutional Neural Network)(컨벌루션 신경망); Deep network(깊은 신경망); MLP(Multi Layer Perceptron)(다층퍼셉트론)
- Citation
- 한국기계기술학회지, v.20, no.6, pp 776 - 782
- Pages
- 7
- Indexed
- KCI
- Journal Title
- 한국기계기술학회지
- Volume
- 20
- Number
- 6
- Start Page
- 776
- End Page
- 782
- ISSN
- 1229-604X
2508-3805
- 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.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - 융합기술공과대학 > Division of Mechatronics Engineering > Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.