genetic algorithm

This study examines the application of the Genetic Algorithm (GA) in the architectural design process with a focus on reproducing aesthetic values such as balance, proportion, harmony, rhythm, and innovation. In today’s world, where the boundaries between art, science, and technology—especially with the advent of artificial intelligence—are increasingly converging, the use of computational tools like genetic algorithms in architectural design has become an inevitable necessity. The fundamental issue addressed in this paper is the challenge of understanding and reproducing the subjective and aesthetic components in architectural design—concepts that are typically considered intuitively and non-quantitatively in traditional design processes. However, genetic algorithms possess the capability to convert these concepts into measurable and quantifiable parameters that can be input into a computational system in the form of a fitness function. Accordingly, the paper’s hypothesis is that by properly designing chromosomes, defining an appropriate objective function, and applying genetic operators such as mutation and crossover, it is possible to generate forms that embody architectural aesthetic values. The research method is qualitative and based on content analysis. In this approach, the authors analyze seven design case studies based on genetic algorithms, examining various stages of architectural design using this algorithm. These stages include encoding forms as digital chromosomes, defining the objective function based on aesthetic criteria, executing an iterative process of generation production, selecting the best forms, and progressively improving design quality.

This article provides a comprehensive review of the impact of evolutionary optimization algorithms on improving learning processes. Evolutionary algorithms, inspired by natural evolution, offer powerful tools for solving complex optimization problems in machine learning. The review covers the theoretical foundations of these algorithms, including Genetic Algorithms, Particle Swarm Optimization, and Differential Evolution, and explores their applications in enhancing learning models. The study compares the performance and effectiveness of these algorithms in various machine learning contexts, highlighting their strengths in optimizing parameters, feature selection, and model structure. Additionally, the review identifies challenges such as parameter tuning, computational complexity, and convergence to local optima, which can limit the effectiveness of these algorithms. The findings suggest that evolutionary optimization algorithms have significant potential to improve learning processes, but also underscore the need for further research to address existing gaps and refine these methods. This review concludes with recommendations for future research directions, emphasizing the importance of developing hybrid algorithms and improving parameter tuning methods to achieve better performance in complex and high-dimensional learning tasks.