DocumentCode :
1841534
Title :
Optimization of recursive branching network
Author :
Al-Mashouq, Khalid ; Al-Hodaif, Yousif
Author_Institution :
King Saud Univ., Riyadh, Saudi Arabia
Volume :
3
fYear :
1999
fDate :
1999
Firstpage :
1491
Abstract :
Recursive branching network (RBN) was proposed by Al-Mashouq (1997) to solve linearly non-separable problems using output-coded perceptrons. It relies on splitting the training patterns, at random, between parallel perceptrons. However, the random splitting mechanism can trap the perceptron in conflicting patterns. Optimized splitting methods are proposed here to ensure meaningful way of splitting. We propose three splitting methods which use different similarity measures between patterns. We examine these methods on five standard data sets. In general, these methods enhance the performance of RBN and in many cases contribute to lowering the network complexity
Keywords :
learning (artificial intelligence); optimisation; pattern classification; perceptrons; vector quantisation; learning patterns; optimization; pattern classification; perceptrons; recursive branching network; splitting methods; vector quantisation; Adaptive algorithm; Clustering algorithms; Decoding; Multi-layer neural network; Neural networks; Optimization methods; Partitioning algorithms; Testing; Vector quantization; Voting;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 1999. IJCNN '99. International Joint Conference on
Conference_Location :
Washington, DC
ISSN :
1098-7576
Print_ISBN :
0-7803-5529-6
Type :
conf
DOI :
10.1109/IJCNN.1999.832589
Filename :
832589
Link To Document :
بازگشت