Proceedings of the 2018 International Conference on Transportation & Logistics, Information & Communication, Smart City (TLICSC 2018)

Recognition and Optimization Algorithm of MNIST Dataset Based on LeNet5 Network Structure

Authors
Hailong Xi, Haiyan Liu, Yu Zhang
Corresponding Author
Hailong Xi
Available Online December 2018.
DOI
10.2991/tlicsc-18.2018.52How to use a DOI?
Keywords
LeNet5 network, MNIST data set, optimization function.
Abstract

This paper analyzes the content composition and detailed structure of the MNIST dataset, introduces the overall level of the traditional LeNet5 network, and proposes an improved algorithm for its hidden layer, optimization function, activation function, etc. of the network layer structure. Optimization, and the effectiveness of the algorithm is verified by experiments. This paper has certain reference value for traditional neural network optimization and improving the correct classification rate of MNIST data sets.

Copyright
© 2018, the Authors. Published by Atlantis Press.
Open Access
This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

Volume Title
Proceedings of the 2018 International Conference on Transportation & Logistics, Information & Communication, Smart City (TLICSC 2018)
Series
Advances in Intelligent Systems Research
Publication Date
December 2018
ISBN
10.2991/tlicsc-18.2018.52
ISSN
1951-6851
DOI
10.2991/tlicsc-18.2018.52How to use a DOI?
Copyright
© 2018, the Authors. Published by Atlantis Press.
Open Access
This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Cite this article

TY  - CONF
AU  - Hailong Xi
AU  - Haiyan Liu
AU  - Yu Zhang
PY  - 2018/12
DA  - 2018/12
TI  - Recognition and Optimization Algorithm of MNIST Dataset Based on LeNet5 Network Structure
BT  - Proceedings of the 2018 International Conference on Transportation & Logistics, Information & Communication, Smart City (TLICSC 2018)
PB  - Atlantis Press
SP  - 322
EP  - 328
SN  - 1951-6851
UR  - https://doi.org/10.2991/tlicsc-18.2018.52
DO  - 10.2991/tlicsc-18.2018.52
ID  - Xi2018/12
ER  -