The widespread use of electronic circuits for communication, computation, automation, and other purposes makes it necessary for diverse circuits to operate in close proximity to each other. All too often, these circuits affect each other adversely. Electromagnetic interference (EMI) has become a major problem for circuit designers. The large number of electronic devices in common use is partly responsible for this trend. In addition, the use of integrated circuits and largescale integration has reduced the size of electronic equipment. As circuitry has become smaller and more sophisticated, more circuits are being crowded into less space, which increases the probability of interference. Electromagnetic compatibility (EMC), then, is the absence of effects due to EMI. Numerical modeling and simulation is essential for understanding the behavior of structures and systems in practically every branch of science and engineering. Unfortunately, the enormous complexity of physical systems often prevents direct approaches where the whole system is characterized using first-principle models (typically systems of partial differential equations (PDEs)) and then simulated on a suitable computer. Divide and conquer techniques have been demonstrated as excellent alternatives to reduce this complexity and to perform efficient numerical simulations with reasonable runtimes. The overall system is first partitioned into well-defined substructures (e.g.,connectors, via fields, coupled interconnect segments), which are characterized separately through approximate reduced-complexity behavioral models, so-called “macromodels.” Macromodels can be identified from terminal responses either in time or frequency domain, leading to compact state-space representations of the broadband dynamics of the structure. Neural-network computational modules have recently gained recognition as an unconventional and useful tool for RF and microwave modeling and design. Neural networks can be trained to learn the behavior of passive/active components/circuits. A trained neural network can be used for high-level design, providing fast and accurate answers to the task it has learned. Neural networks are attractive alternatives to conventional methods such as numerical modeling methods, which could be computationally expensive, or analytical methods which could be difficult to obtain for new devices or empirical modeling solutions whose range and accuracy may be limited. Keywords: Electromagnetic Compatibility, Macromodeling, Artificial Neural Networks