Title :
Neural computing for building statistical macromodels of circuits and systems
Author :
QingShan Zhou ; Yong Zou ; Qinghui Wu ; Minan Li ; Jiandong Hu
Author_Institution :
Training Centre, Beijing Univ. of Posts & Telecommun., China
Abstract :
In this paper, the application of a backpropagation neural network in building statistical macromodels of circuits and systems is studied and the way to analyze the characteristics of the circuits with the help of the macromodel, a well trained BP network with the data measured from the circuit, is discussed. The neural network methodology is a novel way for circuit analysis, and as compared with statistical method, it´s much easier.<>
Keywords :
backpropagation; circuit analysis computing; neural nets; backpropagation neural network; circuit analysis; circuits; neural computing; statistical macromodels; Analytical models; Circuit analysis; Circuit simulation; Circuits and systems; Design for experiments; Feedforward neural networks; Neural networks; Sensitivity analysis; Statistical analysis; Vectors;
Conference_Titel :
TENCON '93. Proceedings. Computer, Communication, Control and Power Engineering.1993 IEEE Region 10 Conference on
Conference_Location :
Beijing, China
Print_ISBN :
0-7803-1233-3
DOI :
10.1109/TENCON.1993.320482
