Quiz Reseau Neurale Graph

Sooy def quiz bi, tontu yi ak leeral yi dañuy feeñ.

1. Lan mooy jumtukaayu ordinatër bu mag bi ci reso neuronal yu bari yi?
   • Yobbu mesaas ak dajale ci digganté node yi ci wetam
   • Gëse ab lëkkale ci kaw ab griy pixel bu takku
   • Xalaatal token bi ci topp
   • Dox yu bari te amul benn njàng
2. Lan moo waral fonction agrégation dekkandoo bu GNN wara nekk permutation budul soppiku?
   • Ngir gaaw ci tàggat yaram
   • Ndax dëkkandoo yi ci graf bi amul benn xeetu njubluwaay
   • Ndax graphe yi dañuy jubal saa yu nekk
   • Ngir wàññi limu parametre yi ba benn
3. Lan mooy 'yootu lu ëpp' ci GNN yu xóot yi?
   • Nataal yi dañuy gëna fësul
   • Graaf bi dafay ñàkk ay boor
   • embeddings node yiy booloo nekk luy nuru lu layers yi di yokk
   • Degrade yi dañuy kalaate ba amul àpp
4. How does a Graph Attention Network differ from a basic GCN layer?
   • It removes all graph edges before message passing
   • It assigns each node a unique text token
   • It guarantees deeper networks cannot over-smooth
   • It learns attention coefficients for neighbors, while the GCN uses degree-normalized propagation weights
5. Ci GNN buñu def ci benn molecule, lan la node yi ak boor yi di màndargaal?
   • Atom ak lëkkaloo chimik
   • Pixel yi ak melo yi
   • Baatu ak tegtal
   • Jëfandikukat yi ak mbind yi
6. Ñaata hop la xibaar mëna dem ci node bi ginaaw L mesaas-passing layers?
   • Saa yu nekk benn hop
   • Ba L hops
   • Graaf bi yépp ci benn layer
   • Amul benn hop
7. What makes GraphSAGE an inductive graph-learning method?
   • It stores a separate free parameter vector for every possible test node
   • It requires one fixed graph and cannot process new nodes
   • It learns neighborhood aggregation functions that can be applied to unseen nodes
   • It replaces node features with graph-level labels
8. In the original GCN propagation rule, what does symmetric degree normalization do to adjacency messages?
   • Sorts neighboring nodes alphabetically
   • Deletes every edge with a low feature value
   • Makes the graph directed by reversing all edges
   • Scales each edge contribution using the inverse square roots of the source and target node degrees