This chapter introduces the concept of combining continuous learning and discrete reasoning in Neuro-Symbolic AI. It begins by examining continuous and discrete spaces, understanding their distinct attributes and contributions to learning and reasoning processes. The chapter explores the proficiency of neural networks in learning from data in continuous domains and the adeptness of symbolic AI systems in logical reasoning within discrete domains. Various methodologies for bridging these two domains are discussed, including Graph Neural Networks, Spiking Neural Networks, and Neuro-Symbolic Goal and Plan Recognition. These techniques show promise for advancing Neuro-Symbolic AI, presenting solutions to the challenge of integrating continuous learning and discrete reasoning within a unified system. The chapter concludes by envisioning future AI systems capable of learning from their environment, reasoning logically, and interacting with the world in a nuanced manner.