This chapter explores neuro-symbolic AI, a hybrid paradigm that integrates the learning capabilities of neural networks with the structured reasoning of symbolic AI. It begins by introducing the foundational concepts and motivations behind this approach, emphasizing its potential to combine perception and logic in a unified framework. The chapter then examines how neural networks and symbolic systems can be coupled, presenting dual-approach architectures that support both data-driven learning and rule-based inference. Key topics include trustworthy decision intelligence, structure learning, and neuro-symbolic reinforcement learning, which extend the framework to dynamic and interactive environments. By bridging statistical learning and symbolic reasoning, neuro-symbolic AI offers a path toward more interpretable, robust, and generalizable AI systems.