Analysis of Feature Extraction Criterion Function Maximum in Nonlinear Multi-layer Feedforward Neural Networks for Pattern Recognition

摘要：

This paper addresses feature extraction criterion function of multi-layer feedforward neural networks with linear output units and nonlinear hidden units. From the minimum mean square error function of the network output, the paper uses the nature of matrix trace and singular value decomposition, deduces the formula for calculating the nonlinear criterion function maximum, then explains the significance of this formula. Finally, simulation examples prove the correctness of the analytic style.

关键词： multilayer feedforward neural network pattern recognition feature extraction criterion function maximum

作者: Cao Junhong Wei Zhuobin Huang Tao Xiong Xianwei

作者单位: Dept. of Logistics Command and Engineering Naval University of Engineering, Tianjin, 300450, China

会议类型: 国际会议

会议名称: 2010 International Conference on Intelligent Computation Technology and Automation(2010 智能计算技术与自动化国际会议 ICICTA 2010)

会议地点: 长沙

会议语种:英文

页码: 655-658

在线出版日期: 2010-05-11（万方平台首次上网日期，不代表论文的发表时间）