Title :
Neural network design for behavioral model generation with shape preserving properties
Author :
Mikulchenko, O. ; Mayaram, Kartikeya
Author_Institution :
Dept. of Electr. & Comput. Eng., Oregon State Univ., Corvallis, OR, USA
Abstract :
A practical method for the design of artificial neural networks (ANN) for behavioral modeling of various devices is presented. The approach has been applied to the modeling of micro-flow sensors and MOS transistors. It is shown that the ANN based behavioral models are accurate and computationally efficient
Keywords :
electronic engineering computing; microsensors; neural nets; semiconductor device models; ANN design; ANN training; MOS transistors; artificial neural networks; behavioral model generation; micro-flow sensors; neural network design; shape preserving properties; Artificial neural networks; Computational modeling; Design methodology; Feedforward systems; MOSFETs; Multilayer perceptrons; Network topology; Neural networks; Neurons; Shape;
Conference_Titel :
Behavioral Modeling and Simulation, 2000. Proceedings. 2000 IEEE/ACM International Workshop on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7695-0893-6
DOI :
10.1109/BMAS.2000.888371
