Porovnat metody
Prohlédněte si vybrané metody vedle sebe; řádky, které se liší, jsou zvýrazněny.
| Grafová neuronová síť× | Stroj s podpůrnými vektory (klasifikace)× | |
|---|---|---|
| Obor≠ | Hluboké učení | Strojové učení |
| Rodina | Machine learning | Machine learning |
| Rok vzniku≠ | 2017 | 1995 |
| Tvůrce≠ | Kipf, T.N. & Welling, M. | Cortes, C. & Vapnik, V. |
| Typ≠ | Deep learning on graph-structured data | Maximum-margin classifier (kernel method) |
| Původní zdroj≠ | Kipf, T.N. & Welling, M. (2017). Semi-Supervised Classification with Graph Convolutional Networks. ICLR. link ↗ | Cortes, C. & Vapnik, V. (1995). Support-Vector Networks. Machine Learning, 20, 273–297. DOI ↗ |
| Další názvy | Grafik Sinir Ağı (GNN), GNN, graph neural net, graph convolutional network | Destek Vektör Makinesi (SVM — Sınıflandırma), support-vector network, SVM classifier, maximum-margin classifier |
| Příbuzné≠ | 4 | 5 |
| Shrnutí≠ | A Graph Neural Network (GNN) is a deep learning method, popularised by Kipf and Welling in 2017 with the Graph Convolutional Network, that learns from the relationships in network (graph) structures made of nodes and edges. It is designed for data that is naturally relational, such as social networks, molecular structures, and recommendation systems. | The Support Vector Machine, introduced by Corinna Cortes and Vladimir Vapnik in 1995, is a classifier that finds the optimal separating hyperplane between classes in a high-dimensional space. It chooses the boundary that leaves the widest possible margin to the nearest training points, which makes its decisions robust on new data. |
| ScholarGateDatová sada ↗ |
|
|