Promotion-based input partitioning of neural network

Shujuan Guo*, Sheng Uei Guan, Weifan Li, Linfan Zhao, Jinghao Song, Mengying Cao

*Corresponding author for this work

Research output: Chapter in Book or Report/Conference proceedingConference Proceedingpeer-review

1 Citation (Scopus)

Abstract

To improve the learning performance and precision of neural network, this paper introduces an input-attribute partitioning algorithm with an aim to increase the promotion among them. If a better performance could be obtained by training some attributes together, it is considered that there is positive effect among these attributes. It is assumed that by putting attributes, among which there are positive effect, a lower error can be obtained. After partitioning, multiple learners were employed to tackle each group. The final result is obtained by integrating the result of each learner. It turns out that, this algorithm actually can reduce the classification error in supervised learning of neural network.

Original languageEnglish
Title of host publicationProceedings of the 9th International Symposium on Linear Drives for Industry Applications, LDIA 2013
PublisherSpringer Verlag
Pages179-186
Number of pages8
EditionVOL. 3
ISBN (Print)9783642406324
DOIs
Publication statusPublished - 2014
Externally publishedYes
Event9th International Symposium on Linear Drives for Industry Applications, LDIA 2013 - Hangzhou, China
Duration: 7 Jul 201310 Jul 2013

Publication series

NameLecture Notes in Electrical Engineering
NumberVOL. 3
Volume272 LNEE
ISSN (Print)1876-1100
ISSN (Electronic)1876-1119

Conference

Conference9th International Symposium on Linear Drives for Industry Applications, LDIA 2013
Country/TerritoryChina
CityHangzhou
Period7/07/1310/07/13

Keywords

  • Input attribute grouping
  • Neural network
  • Promotion

Fingerprint

Dive into the research topics of 'Promotion-based input partitioning of neural network'. Together they form a unique fingerprint.

Cite this