Hyperparameter Tuning for Self-Organizing Maps

Self-Organizing Maps (SOMs) are widely used across a wide range of domains, including visualization, feature map generation, pattern recognition, and classification. Despite their simplicity, SOMs are able to effectively reduce the dimensionality of data while preserving its inherent structure, making it easier to analyze and interpret complex datasets. In this paper, we propose a methodology for hyperparameter tuning in SOMs, highlighting the importance of key parameters and optimization techniques to enhance SOMs performance. We benefit from SMAC, a powerful tool for optimizing SOMs parameters. Our experimental results, based on a real case study, demonstrate that careful tuning of these parameters is crucial for achieving optimal convergence and avoiding overfitting or excessive computational costs. By implementing these advanced tuning methods, it is possible to significantly enhance the accuracy, efficiency, and applicability of SOMs in diverse data analysis contexts.