The Enhancement Arithmetic of BP Neural Network Based on Target Optimizing

DOI

10.2991/cmsa-18.2018.32How to use a DOI?

Keywords

BP neural network; quadratic programming; target optimizing

Abstract

BP neural network recognition algorithm was used to carry through target recognition, then we adopted quadratic programming and generalized least squares to optimize the network weights and thresholds, at last the algorithm formula was deduced. In the neural network training process, a tendentious training was achieved. Experiments show that the algorithm had a better effect.

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)

TY  - CONF
AU  - Shuang Shi
AU  - Daqi Zhang
AU  - Pengfei Feng
AU  - Lingli Han
PY  - 2018/04
DA  - 2018/04
TI  - The Enhancement Arithmetic of BP Neural Network Based on Target Optimizing
BT  - Proceedings of the 2018 International Conference on Computer Modeling, Simulation and Algorithm (CMSA 2018)
PB  - Atlantis Press
SP  - 137
EP  - 141
SN  - 1951-6851
UR  - https://doi.org/10.2991/cmsa-18.2018.32
DO  - 10.2991/cmsa-18.2018.32
ID  - Shi2018/04
ER  -