This paper discusses the training of deep neural networks (DNNs) for electromagnetic problems. The main concerns include how to modify EM problems to take the advantage of the deep learning techniques and how to tailor conventional deep learning concepts with electromagnetic domain knowledge, which has been overlooked by most existing DNN based EM research. A 1×8 patch antenna array has been adopted as the test vehicle for investigation, with the aim to use deep learning for radiation pattern synthesis. It is analyzed via electromagnetic simulation first to collect sufficient training data sets containing different combinations of excitation signals and corresponding radiation patterns. These data are then pre-processed and passed to DNNs for training to imitate the mapping between excitation signals and radiation patterns. With careful feature selection and DNN architecture optimizations, two DNN models are obtained eventually. One of them aims at forward radiation synthesis in any certain excitation condition, and the other seeks out backward excitation signals needed for a given radiation pattern, and both achieved an accuracy over 80%. This paper may provide enlightenment and reference in applying deep learning to electromagnetic problems in terms of feature selection and architecture modification.