Deep learning based on artificial neural networks (ANNs) is a powerful machine-learning method that, in recent years, has been successfully used to realize tasks such as image classification, speech recognition, and language translation, among others, that are usually simple for human beings but extremely difficult for machines. This is one reason deep learning is considered one of the main enablers for realizing artificial intelligence (AI). The current methodology in deep learning consists of employing a data-driven approach to identify the best architecture of an ANN that allows input-output data pairs to be fitted. Once the ANN is trained, it is capable of responding to never-observed inputs by providing the optimum output based on past acquired knowledge. In this context, a recent trend in the deep-learning community complements purely data-driven approaches with prior information based on expert knowledge. In this article, we describe two methods that implement this strategy to optimize wireless communication networks. In addition, we provide numerical results to assess the performance of the proposed approaches compared with purely data-driven implementations.