From Evolution to Intelligence: Exploring the Synergy of Optimization and Machine Learning

The rapid advancements in machine learning (ML) and evolutionary optimization techniques (EOT) have opened up new avenues for solving complex problems across diverse scientific domains. ML algorithms utilize a provided dataset to construct a proficient predictive or descriptive model. Evolutionary optimization algorithms, on the other hand, are a class of metaheuristic optimization methods that simulate the process of evolution by refining a population of potential solutions iteratively over generations to discover optimal or nearly optimal solutions to complex problems. A multitude of proposals have been sequentially put forth to address optimization problems/methodologies within the realm of ML. It is imperative to conduct a thorough examination and implementation of evolutionary optimization methods within the context of ML in order to provide direction for the advancement of research in both optimization and ML. Hence, this chapter provides a focused examination of the intersection between ML and EOT, which have been utilized in tandem to tackle a diverse array of scientific challenges. Furthermore, the present chapter delves into the potential areas of investigation that could enhance the efficacy of ML-EOT models.