Neural Network for Circuit Models of Monolithic InAlN/GaN NAND and NOR Logic Gates | IEEE Conference Publication | IEEE Xplore

Neural Network for Circuit Models of Monolithic InAlN/GaN NAND and NOR Logic Gates


Abstract:

This paper presents large signal circuit models of InAlN/GaN monolithic integrated NAND and NOR logic gates. The models are calibrated automatically by artificial neural ...Show More

Abstract:

This paper presents large signal circuit models of InAlN/GaN monolithic integrated NAND and NOR logic gates. The models are calibrated automatically by artificial neural network (NN). Appropriate setting and properties for NN training is described. Very high accuracy of the proposed models is observed. The features and accuracy of NAND and NOR logic gate models prepared by NN are compared with standard empirical compact models based on the transistor level. The advantages and limitations of NN for circuit modeling are discussed. Good agreement between measurements and simulations confirms the validity of the proposed models and methodology for model generation of logic gates.
Date of Conference: 16-18 April 2019
Date Added to IEEE Xplore: 13 June 2019
ISBN Information:
Conference Location: Mykonos, Greece

I. Introduction

Progress in the development of gallium nimde (GaN) high electron mobility transistors (HEMTs) puts them in the position of one of the leading technologies ready to satisfy unceasing demand for high frequency and power applications because of their excellent electronic properties, especially high electron saturation velocity and high critical electric field [1 – 4] . However, there are still a lot of areas to be investigated in order to extract and utilize the favorable GaN material properties. Among them the most important is to develop new GaN specific processes, structure design, characterization, and simulation techniques.

References

References is not available for this document.