Deep learning techniques have revolutionized machines' ability to learn and perform complex tasks autonomously. Within the world of deep learning, graph neural networks (GNNs) have emerged as a powerful tool. These networks are designed to model complex relationships between structured data, such as graphs and networks. Their ability to capture the structure and interconnection of data makes them particularly effective in applications involving interrelated elements.

The extensive scope of application of deep learning techniques, and GNNs in particular, is contributing to significant advances in various scientific and technical disciplines. For this reason, undergraduate students, as well as master's and doctoral students, increasingly need to understand these algorithms in order to apply them in their academic work (undergraduate and master's theses, etc.) and research.

Translated with DeepL.com (free version)

Deep learning techniques have revolutionized the ability of machines to learn and perform complex tasks autonomously. The extensive scope of application of deep learning techniques is contributing to significant advances in various scientific and technical disciplines. For this reason, students in different university degrees, as well as master's and doctoral students, increasingly need to know these algorithms in order to apply them in their academic work (final degree projects, master's theses, etc.) and research.