Deep Learning Course (NYU, Spring 2020) - Week 13 – Practicum: Graph Convolutional Neural Networks (GCN)

Course website: http://bit.ly/pDL-home Playlist: http://bit.ly/pDL-YouTube Speaker: Alfredo Canziani Week 13: http://bit.ly/pDL-en-13 0:00:00 – Week 13 – Practicum PRACTICUM: http://bit.ly/pDL-en-13-3 In this section, we introduce Graph Convolutional Network (GCN) which is one type of architecture that utilizes the structure of data. Actually, the concept of GCNs is closely related to self-attention. After understanding the general notation, representation and equations of GCN, we delve into the theory and code of a specific type of GCN known as Residual Gated GCN. 0:00:47 – Introduction to Graph Convolutional Network (GCN) 0:16:32 – Residual Gated GCN Theory and Code 0:34:58 – Gated GCNs Implementation Code and Training