06:47

Topology-aware Graph Neural Network | Distinguished* MSc | **Oral Presentation** | GRAIL MICCAI 2024

07:26

Topology-Preserving GNNs for Brain Graph Super-Resolution | Distinguished* MSc | PRIME MICCAI 2024

07:53

Generative Hypergraph Neural Networks for Data Fusion | **Oral Presentation** | PRIME-MICCAI 2024

09:44

Diversity-Based Hyperedge Sampling in GNN Learning | MICCAI MLMI 2024

07:58

A Universal Federation of a Mixture of Highly Heterogeneous Learning Tasks | MICCAI MLMI 2024

56:35

[RISE-FIFAI Summer School 2024] Federated Learning Lab Session

08:45

[Deep Graph Learning] 6.7 Evaluation measures for generative GNNs

32:47

[Deep Graph Learning] 6.6 Generative Graph U-Net

09:30

[Deep Graph Learning] 6.5 Supervised conditional generation on graphs

35:55

[Deep Graph Learning] 6.4 Unconditional one-shot graph generation

12:28

[Deep Graph Learning] 6.3 Unconditional sequential graph generation

20:03

[Deep Graph Learning] 6.2 Self-supervised/unsupervised generative GNNs

33:21

[Deep Graph Learning] 6.1 Overview of supervised generative GNNs

20:54

[Deep Graph Learning] 5.4 Graph Isomorphism Network Expressive nets

37:44

[Deep Graph Learning] 5.3 GNN expressiveness

13:38

[Deep Graph Learning] 5.2 Node permutation equivariance in GNNs

33:53

[Deep Graph Learning] 5.1 Node permutation invariance in GNNs

20:46

[Deep Graph Learning] 4.6 GNN inductive vs transductive learning

21:35

[Deep Graph Learning] 4.5 Generalized GNN layer and Dropout

16:36

[Deep Graph Learning] 4.4 GNN batch normalization layer

06:45

[Deep Graph Learning] 4.3 Recap on GNN sampling methods

49:33

[Deep Graph Learning] 4.2 Batching and GNN sampling methods

15:29

[Deep Graph Learning] 4.1 Point, batch and mini-batch gradient descent

19:03

[Deep Graph Learning] 3.5 Global and local aggregation methods

12:35

[Deep Graph Learning] 3.4 GCN layer operations

22:24

[Deep Graph Learning] 3.3 Graph pooling & embedding aggregation

32:20

[Deep Graph Learning] 3.2 GNN inductive capability & graph-based learning

01:06:25

[Deep Graph Learning] 3.1 GCN training and loss optimization

46:08

[Deep Graph Learning] 2.5 Generalized GCN node and layer updates

43:09

[Deep Graph Learning] 2.4 Analyzing a single GCN layer

21:34

[Deep Graph Learning] 2.3 Shallow graph node embedding

23:49

[Deep Graph Learning] 2.2 The evolving landscape of feature embedding

51:48

[Deep Graph Learning] 2.1 The logic behind graph-based learning

23:46

[Deep Graph Learning] 1.3 Graph learning tasks (node, edge and graph based)

01:04:19

[Deep Graph Learning] 1.2 The graph matrix: from topology to resilience

53:35

[Deep Graph Learning] 1.1 Graph types

23:04

[Intuitive Deep Learning] 5.4 Overview of ResNet, DenseNet and UNet

01:04:40

[Intuitive Deep Learning] 5.3 Control layer variance with batch normalization

37:01

[Intuitive Deep Learning] 5.2 The logic behind residual connections

45:52

[Intuitive Deep Learning] 5.1 Shattered gradients in sequential learning

38:03

[Intuitive Deep Learning] 4.4 CNNs: Downsampling | upsampling | transposed convolution

01:05:02

[Intuitive Deep Learning] 4.3 CNNs: invariance | equivariance

19:22

[Intuitive Deep Learning] 4.2 CNNs: invariance | equivariance

57:39

[Intuitive Deep Learning] 4.1 The logic behind CNNs

01:13:24

[Intuitive Deep Learning] 3.5 Hands-on examples:Shallow to deep nets with backprop and batching

33:45

[Intuitive Deep Learning] 3.4 Batch layer-wise normalization (animated)

31:48

[Intuitive Deep Learning] 3.3 Backpropagation: forward and reverse differentiation modes

50:15

[Intuitive Deep Learning] 3.2 Gradient Descent & Computation Graphs

50:35

[Intuitive Deep Learning] 3.1 Activation functions

21:05

[Intuitive Deep Learning] 2.1 Fully-connected multi-layer network coded in matrices

38:31

[Intuitive Deep Learning] 2.1 Fully-connected single-layer network coded in matrices

47:35

[Intuitive Deep Learning] 1.6 Generalizaed matrix factorization | Multiview data clustering using MF

50:32

[Deep Learning Matrix Reloaded] From spanning sets to deep matrix factorization (part 2)

27:43

[Deep Learning Matrix Reloaded] Supervised learning expressed into matrices (part 1)

21:46

[Intuitive Deep Learning] 1.5 Spanning sets & matrix factorization for data representation | PCA

01:17:02

[Intuitive Deep Learning] 1.4 Spanning sets & matrix factorization for data representation | PCA

30:36

[Intuitive Deep Learning] 1.3 Supervised linear and non-linear classifiers coded in matrices

20:04

[Intuitive Deep Learning] 1.2 Supervised linear and nonlinear multiregression coded in matrices

47:23

[Intuitive Deep Learning] 1.1 Supervised linear and non-linear regression coded in matrices

01:58:59

[BASIRA Seminar] Fairness in Machine Learning: Metrics and Algorithms | Zhimeng Jiang