Improving the performance of a convolutional neural network through manipulation of convolution = 컨볼루션의 조작을 통한 컨볼루션 신경망의 성능향상에 관한 연구

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 17
  • Download : 0
Convolutional neural networks (CNNs) have been successfully applied to a variety of vision tasks, and most of this success comes from research on network structure. However, in spite that convolution is the most important component of CNN, little research has been done about convolution itself, and attempts have been made recently to overcome the limitation of existing convolution. The shape of conventional convolution is restricted, and it is assigned at the stage of configuration of network structure. Usually, extending the size of convolution or stacking more convolution is used for enlarging the receptive field of the network, but this approaches might reduce the efficiency of network due to increases of network depth or the number of parameters. In this dissertation, we describe methodologies for improving the performance of the network through manipulating convolution. The performance of the neural network can be evaluated in terms of accuracy and speed. The earlier part of this paper, we describe the research related to the improvement of accuracy and the studies about improving the speed of the network in the latter part.
Advisors
Kim, Junmoresearcher김준모researcher
Description
한국과학기술원 :전기및전자공학부,
Publisher
한국과학기술원
Issue Date
2019
Identifier
325007
Language
eng
Description

학위논문(박사) - 한국과학기술원 : 전기및전자공학부, 2019.2,[viii, 69 p. :]

Keywords

Deep learning▼aConvolutional Neural Network (CNN)▼aconvolution▼areceptive field▼aaccuracy▼aprocessing time; 딥러닝▼a컨볼루션 신경망▼a컨볼루션▼a수용영역▼a정확도▼a연산속도

URI
http://hdl.handle.net/10203/265162
Link
http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=842382&flag=dissertation
Appears in Collection
EE-Theses_Ph.D.(박사논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0