Deep-learning-based precise characterization of microwave transistors using fully-automated regression surrogates

Accurate models of scattering and noise parameters of transistors are instrumental in facilitating design procedures of microwave devices such as low-noise amplifiers. Yet, data-driven modeling of transistors is a challenging endeavor due to complex relationships between transistor characteristics and its designable parameters, biasing conditions, and frequency. Artificial neural network (ANN)-based methods, including deep learning (DL), have been found suitable for this task by capitalizing on their flexibility and generality. Yet, rendering reliable transistor surrogates is hindered by a number of issues such as the need for finding good match between the input data and the network architecture and hyperparameters (number and sizes of layers, activation functions, data pre-processing methods), possible overtraining, etc. This work proposes a novel methodology, referred to as Fully Adaptive Regression Model (FARM), where all network components and processing functions are automatically determined through Tree Parzen Estimator. Our technique is comprehensively validated using three examples of microwave transistors and demonstrated to offer a competitive edge over the state-of-the-art methods in terms of modeling accuracy and handling the aforementioned issues pertinent to standard ANN-based surrogates.