ANNs for Fast Parameterized EM Modeling: The State of the Art in Machine Learning for Design Automation of Passive Microwave Structures
Feng Feng, Weicong Na, Jing Jin, Wei Zhang, Qi‐Jun Zhang
Abstract
Artificial neural networks (ANNs) are information processing systems, with their design inspired by studies of the ability of the human brain to learn from observations and generalize by abstraction. Researchers have investigated a variety of important applications utilizing the ability of ANNs to perform the modeling and optimization of microwave components and circuits, such as high-speed very large-scale integration (VLSI) interconnects [1]-[3], spiral inductors [4], microwave field-effect transistors (FETs) [5], [6], heterojunction bipolar transistors [7], [8], high-electron mobility transistors [9], [10], filters [11]-[14], power amplifiers [15]-[17], oscillators [18], transmitters [19], receivers [20], digital predistortion [21], microelectromechanical systems [22], wireless power transfer [23], and multiphysics design [24], [25].