This paper provides a comprehensive review of optimization techniques applied in machine learning (ML) and neural networks (NN), focusing on the relevance of these methods. Optimization techniques are critical for improving the performance and efficiency of ML and NN models, addressing key computational challenges and enabling innovative applications. The primary objective of this study is to identify widely used methods, such as genetic algorithms, particle swarm optimization, and gradient boosting. A bibliometric analysis of 52,561 publications from 2020 to 2024 was conducted using Scopus, employing metrics like citation counts, H-index, and keyword frequency to assess the impact and trends of these techniques. The analysis revealed that genetic algorithms and particle swarm optimization were the most frequently employed methods, with IEEE Access emerging as the leading journal for relevant studies. Trends in the adoption of optimization methods highlight their increasing importance in enhancing model performance, scalability, and computational efficiency. This research provides a foundation for future studies, offering a clear roadmap for the selection and application of optimization techniques to drive advancements in ML and NN.