Abstract
<jats:p>The increasing demand for ultra-high data rates, low latency, and reliable connectivity in next-generation wireless networks necessitates the development of intelligent and adaptive antenna systems. Traditional signal processing methods, while effective under controlled conditions, often struggle to address the dynamic channel variations, interference, and multipath propagation encountered in 5G, 6G, and beyond. The integration of artificial intelligence (AI) into signal processing frameworks offers transformative capabilities, enabling predictive beamforming, adaptive channel estimation, interference mitigation, and efficient resource allocation. This chapter provides a comprehensive analysis of AI-driven techniques applied to antenna systems, highlighting hybrid approaches that combine classical signal processing with machine learning, optimization algorithms for antenna design, and cognitive reconfigurable architectures. Hardware considerations, computational efficiency, and energy-aware design strategies are discussed to demonstrate practical implementation feasibility. Performance evaluations illustrate significant improvements in spectral efficiency, signal-to-noise ratio, and reliability compared with conventional methods, while also addressing challenges such as generalization, dataset requirements, and real-time adaptability. The chapter concludes with emerging trends and future research directions, emphasizing the critical role of AI-enabled antenna systems in achieving resilient, high-capacity, and intelligent next-generation networks.</jats:p>