Research And Implementation of Iterative MapReduce Based On BP Algorithm

DOI

10.2991/icmemtc-16.2016.98How to use a DOI?

Keywords

MapReduce; BP algorithm; iteration; Control system in the K/TGR radioswitch.

Abstract

The Error Back Propagation is iterative, the way of implementing it using the iterative MapReduce framework is presented. To solve the shortage of the traditional MapReduce framework in iterative program, the iterative MapReduce framework has added a transmitting module. Through the simulation of the control system in the K/TGR radioswitch to get the training sample. Training the sample based on the traditional framework and the iterative framework on Hadoop. The experimental results show that the BP algorithm based on the iterative framework demonstrated faster speed and higher accuracy. The iterative framework can effectively reduce the training time and avoid the problem in iterative calculation.

Copyright

© 2016, 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  - Yu Yang
AU  - Longjun Zhang
PY  - 2016/04
DA  - 2016/04
TI  - Research And Implementation of Iterative MapReduce Based On BP Algorithm
BT  - Proceedings of the 2016 3rd International Conference on Materials Engineering, Manufacturing Technology and Control
PB  - Atlantis Press
SP  - 507
EP  - 510
SN  - 2352-5401
UR  - https://doi.org/10.2991/icmemtc-16.2016.98
DO  - 10.2991/icmemtc-16.2016.98
ID  - Yang2016/04
ER  -