摘要
描述Cascade-correlation和RBF-DDA(dynamic decay adjustment for RBFs)神经网络算法,以Proben1中的3个数据库(癌症数据库、糖尿病数据库、心脏病数据库)为例,阐述两种算法在训练神经网络中的应用,并对比这两种算法的性能。
This article describes cascade-correlation algorithm and dynamic decay adjustment for RBFs algorithm, and uses three database of Probenl (cancer,diabetes and heart)to probe and compare the application of the two algorithms in neural network training.
出处
《石河子大学学报(自然科学版)》
CAS
2005年第5期650-653,共4页
Journal of Shihezi University(Natural Science)