Title :
Self-organizing neural grove
Author :
Inoue, H. ; Sugiyama, Kiyotaka
Author_Institution :
Dept. of Electr. Eng. & Comput. Sci., Kure Nat. Coll. of Technol., Hiroshima, Japan
Abstract :
Recently, multiple classifier systems have been used for practical applications to improve classification accuracy. Self-generating neural networks (SGNN) are one of the most suitable base-classifiers for multiple classifier systems because of their simple settings and fast learning ability. However, the computation cost of the multiple classifier system based on SGNN increases in proportion to the numbers of SGNN. In this paper, we propose a novel pruning method for efficient classification and we call this model a self-organizing neural grove (SONG). Experiments have been conducted to compare the SONG with bagging and the SONG with boosting, the multiple classifier system based on C4.5, and support vector machine (SVM). The results show that the SONG can improve its classification accuracy as well as reducing the computation cost.
Keywords :
learning (artificial intelligence); neural nets; pattern classification; support vector machines; SGNN; SONG model; SONG with bagging; SONG with boosting; SVM; classification accuracy; learning ability; multiple classifier systems; pruning method; self-generating neural networks; self-organizing neural grove model; support vector machine; Accuracy; Bagging; Boosting; Data mining; Memory management; Neural networks; Support vector machines; bagging; boosting; neural network ensembles; self-organization;
Conference_Titel :
Intelligent Data Acquisition and Advanced Computing Systems (IDAACS), 2013 IEEE 7th International Conference on
Conference_Location :
Berlin
Print_ISBN :
978-1-4799-1426-5
DOI :
10.1109/IDAACS.2013.6662697
