Simulated annealing and tabu search for optimization of neural networks

被引:0
|
作者
Yamazaki, A [1 ]
Ludermir, TB [1 ]
de Souto, MCP [1 ]
机构
[1] Univ Fed Pernambuco, Ctr Informat, BR-50732970 Recife, PE, Brazil
关键词
D O I
暂无
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
This paper shows results of using simulated annealing and tabu search for optimizing neural network architectures and weights. The algorithms generate networks with good generalization performance (mean classification error for the test set was 5.28% for simulated annealing and 2.93% for tabu search) and low complexity (mean number of connections used was 11.68 out of 36 for simulated annealing and 11.49 out of 36 for tabu search) for an odor recognition task in an artificial nose.
引用
收藏
页码:510 / 518
页数:9
相关论文
共 50 条