Efficient‐driven Approaches Related to Meta‐Heuristic Algorithms using Machine Learning Techniques
Ashima Arya, Swasti Singhal, Rashika Bangroo · 2024
The amount of research evaluating the use of machine learning (ML) to determine effective, profitable, and adaptable metaheuristics has drawn more interest in recent years. Numerous of these stochastic and metaheuristics algorithms have produced high-quality outcomes and represent cutting-edge optimization techniques. Although different techniques have been offered, this study issue lacks a systematic survey and classification. In this work, several options for incorporating ML into metaheuristics are examined. It defines synergy in a way that may be applied to the wide variety of methods for achieving this goal. A comprehensive taxonomy is provided according to the search component that is being considered. This taxonomy encompasses not only the intended optimization issue but also minimal metaheuristics components and elevated components. In addition to this, one of our objectives is to encourage scholars working in optimization to incorporate concepts derived from ML into metaheuristics. Some unanswered research concerns that need additional in-depth investigation into this topic have been highlighted in this chapter.