GEOMETRICAL LEARNING ALGORITHM FOR MULTILAYER NEURAL NETWORKS IN A BINARY FIELD

被引:8
|
作者
PARK, SK
KIM, JH
机构
[1] TENNESSEE TECHNOL UNIV,DEPT ELECT ENGN,COOKEVILLE,TN 38505
[2] UNIV SW LOUISIANA,CTR ADV COMP STUDIES,LAFAYETTE,LA 70504
关键词
BINARY FIELD; CONVERGENCE; HARDLIMITING NEURONS; INTEGER WEIGHTS; LEARNING; NEURAL NETWORKS;
D O I
10.1109/12.238491
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
This correspondence introduces a geometrical expansion learning algorithm for multilayer neural networks using unipolar binary neurons with integer connection weights, which guarantees convergence for any Boolean function. Neurons in the hidden layer develop as necessary without supervision. In addition, the computational amount is much less than that of the backpropagation algorithm.
引用
下载
收藏
页码:988 / 992
页数:5
相关论文
共 50 条