This chapter focuses on the integration of artificial intelligence methodologies into computational modeling of human behavior, emphasizing the interdisciplinary convergence of cognitive psychology, neuroscience, and machine learning. It describes the evolution from traditional behavioral modeling approaches to advanced deep learning, such as neural networks and probabilistic models, to achieve more nuanced simulations of human cognition and social interactions. Furthermore, it highlights the enhanced capacity of Bayesian frameworks to incorporate prior knowledge and manage uncertainty, thereby providing a more robust theoretical foundation compared to classical frequentist methods. In addition, it summarizes the application of reinforcement learning paradigms to emulate human learning processes and strategic decision-making. With the development of human-centered artificial intelligence (HCAI), AI technologies have not only advanced human behavior modeling but also introduced new perspectives for the design of intelligent systems, especially in areas like simulating human cognition, emotion, and collective behaviors. This chapter offers a comprehensive analysis of state-of-the-art AI-driven modeling strategies, highlighting their potential to yield deeper insights into complex human behaviors and inform the development of intelligent systems capable of adaptive human cognition.