23:08
Convolutional graph neural networks and attention mechanisms
17:58
Feed-forward neural networks for graph processing
23:22
10.2 Generative Adversarial Networks
23:20
Spatial Attention in Computer Vision: The Spatial Transformer
09:52
SENets: Channel-Wise Attention in Convolutional Neural Networks
19:55
1.1 An Introduction to Neural Networks
26:55
9.3 Policy Gradients
27:19
8.2 Backpropagation and Gradient-Based Visualization in Convolutional Neural Networks
29:07
8.3 Case Studies of Convolutional Neural Networks
44:21
9.2 Value Function Learning and Q-Learning [Temporal Difference/TD-Learning]
11:05
4.3 Dropout
15:26
3.2 Practical Aspects of Neural Network Training [Feature Preprocessing, Initialization, Tuning]
22:29
7.2 Applications of Recurrent Neural Networks
15:50
3.4 First-Order Gradient Descent Methods
21:53
4.1 Model Generalization and the Bias-Variance Trade-Off
36:24
8.1 Convolutional Neural Networks
18:24
3.5 Second-Order Optimization in Neural Networks
32:00
7.3 Long Short-Term Memory [LSTM] and Gated Recurrent Units [GRU]
14:31
2.4: The Softmax Activation Function and Multinomial Logistic Regression
44:45
6.1 Restricted Boltzmann Machines
14:40
5.1 Radial Basis Function Networks
12:25
3.6 Batch Normalization
13:41
4.2 Penalty-based Regularization
15:02
1.4: Multilayer Neural Networks
18:31
3.3 The Vanishing and Exploding Gradient Problems
24:08
10.1 Attention Mechanisms for Deep Learning
12:01
2 1: Connections of classical machine learning models with neural networks
11:44
2.3 Logistic Regression and Comparison with Perceptron/Widrow-Hoff/SVM
13:16
2.2: Widrow-Hoff Learning: A Neural Model for Linear Regression/Classfication/Fisher Discriminant
19:06
10.3 Kohonen Self-Organizing Map
26:49
7.1 Recurrent Neural Networks
12:51
4.4 Unsupervised Pretraining
41:41
9.1 Deep Reinforcement Learning: The Basics
15:25
1.2 Training a Perceptron
12:00
1.3 Activation and Loss Functions
28:55
4.5 Regularized Autoencoders [Denoising, Contractive, Variational]
13:29
2.5 The Autoencoder for Unsupervised Representation Learning
11:57
2.8: Word2Vec: The Skip Gram Model and Connections to Recommender Systems
12:10
2.7: Neural Model for Recommender Systems: Row-Index-to-Row-Value Autoencoder
13:45
2.6 Singular value decomposition with an autoencoder
47:54
3.1 Backpropagation in Neural Networks
X
About
Tags