Artificial Neural Networks (ANN) recently gained recognition as an unconventional alternative to modeling and design tasks in RF and microwaves CAD. Following the first special issue of this topic published in the May 1999 issue of the International Journal of RF and Microwave CAE, there has been a substantial increase of interests and activities in ANN from the RF and microwave community. ANN computation is very fast. ANN can learn and generalize from data allowing model development even when component formulas are unavailable. ANNs are universal approximators applicable to linear and nonlinear problems and at device or circuit levels. ANN are being applied to modeling and design of microstrip and CPW circuits, multilayer interconnects, embedded passive components, printed antennas, semiconductor devices, measurement standards, filters, amplifiers and so on. Further advances in embedding microwave information into neural networks lead to new knowledge based methods for robust electrical modeling. There are increased initiatives in integration of neural network capabilities into circuit design processes, for example, embedding neural networks in circuit optimization, statistical design, global modeling, and computational electromagnetics. This special issue will provide a common forum to showcase the state-of-the-art and discuss the future of applications of ANN to RF and microwave design.