A Case Study on Stacked Generalization with Software Reliability Growth Modeling Data

摘要：

We study on stacked generalization performance with software reliability growth data by using a pseudoinverse learning algorithm for feedforward neural networks. The experiments show that for noisy data, using stacked generalization can not improve the network performance when overtrained networks are engaged. With properly trained networks, stacked generalization can improve the network generalization performance.

关键词： Stacked Generalization Pseudoinverse Learning Algorithm Feedforward Neural Network Software Reliability Growth Data.

作者: Ping Guo Michael R. Lyu

作者单位: College of Information Science,Beijing Normal University,Beijing, 100875, P.R. China Dept. of Comp. Sci. & Engr.,The Chinese University of Hong Kong,Shatin, NT, Hong Kong

会议类型: 国际会议

会议名称: 8th International Conference on Neural Information Processing(ICONIP 2001)(第八届国际神经信息处理大会)

会议地点: 上海

会议语种:英文

页码: 1359-1364

在线出版日期: 2001-11-14（万方平台首次上网日期，不代表论文的发表时间）