Title :
Robustness analysis of feedforward neural networks composed of threshold neurons
Author :
Yang, Liangtu ; Hu, Dongcheng ; Luo, Yupin ; Zhang, Xiaozhong
Author_Institution :
Dept. of Autom., Tsinghua Univ., Beijing, China
Abstract :
Based on a stochastic model for inputs and weights, and in view of the disturbance of correlative and large input and weight errors, a general algorithm to obtain the output error feature of multilayered feedforward neural networks composed of threshold neurons is proposed by adopting a statistical approach. The result of computer simulation indicates the correctness and excellent precision of the algorithm
Keywords :
errors; feedforward neural nets; multilayer perceptrons; stability; statistical analysis; stochastic processes; computer simulation; feedforward neural networks; inputs; multilayered neural networks; output error feature; robustness analysis; statistical approach; stochastic model; threshold neurons; weights; Computer errors; Feedforward neural networks; Gaussian distribution; HDTV; Multilayer perceptrons; Neural networks; Neurons; Random variables; Robustness; Stochastic processes;
Conference_Titel :
Intelligent Processing Systems, 1997. ICIPS '97. 1997 IEEE International Conference on
Conference_Location :
Beijing
Print_ISBN :
0-7803-4253-4
DOI :
10.1109/ICIPS.1997.672833
