Abstract
<jats:p>This volume highlights evolving machine learning methodologies and their deployment across real-world application domains. The emphasis is on optimization algorithms, data-efficient learning strategies, advanced generalization mechanisms, reinforcement-based learning, and hybrid learning structures combining probabilistic, statistical, and deep representation techniques. Research on interpretability, responsible ML governance, model fairness, adversarial robustness, and automated ML pipelines is encouraged. Applied studies addressing healthcare analytics, smart infrastructure, financial modeling, environmental forecasting, and urban intelligence are welcomed. The aim is to support the development of adaptive, transparent, and scalable ML systems capable of generating reliable predictions and actionable insights across diverse operational contexts.</jats:p>