Deep Learning — Andreas Geiger

46 videos • 195,158 views • by Tübingen Machine Learning Lecture: Deep Learning (Prof. Andreas Geiger, University of Tübingen) Course Website with Slides, Lecture Notes, Problems and Solutions: https://uni-tuebingen.de/fakultaeten/... This course introduces the practical and theoretical principles of deep neural networks. Amongst other topics, we cover computation graphs, activation functions, loss functions, training, regularization and data augmentation as well as various basic and state-of-the-art deep neural network architectures including convolutional networks and graph neural networks. The course also addresses deep generative models such as auto-encoders, variational auto-encoders and generative adversarial networks. In addition, applications from various fields will be presented throughout the course. After this course, students should be able to develop and train deep neural networks, reproduce research results and conduct original research in this area.
1
Deep Learning - Lecture 1.1 (Introduction: Organization)
Tübingen Machine Learning
Download
2
Deep Learning - Lecture 1.2 (Introduction: History of Deep Learning)
Tübingen Machine Learning
Download
3
Deep Learning - Lecture 1.3 (Introduction: Machine Learning Basics)
Tübingen Machine Learning
Download
4
Deep Learning - Lecture 2.1 (Computation Graphs: Logistic Regression)
Tübingen Machine Learning
Download
5
Deep Learning - Lecture 2.2 (Computation Graphs: Computation Graphs)
Tübingen Machine Learning
Download
6
Deep Learning - Lecture 2.3 (Computation Graphs: Backpropagation)
Tübingen Machine Learning
Download
7
Deep Learning - Lecture 2.4 (Computation Graphs: Educational Framework)
Tübingen Machine Learning
Download
8
Deep Learning - Lecture 3.1 (Deep Neural Networks: Backpropagation with Tensors)
Tübingen Machine Learning
Download
9
Deep Learning - Lecture 3.2 (Deep Neural Networks: The XOR Problem)
Tübingen Machine Learning
Download
10
Deep Learning - Lecture 3.3 (Deep Neural Networks: Multi-Layer Perceptrons)
Tübingen Machine Learning
Download
11
Deep Learning - Lecture 3.4 (Deep Neural Networks: Universal Approximation)
Tübingen Machine Learning
Download
12
Deep Learning - Lecture 4.1 (Deep Neural Networks II: Output and Loss Functions)
Tübingen Machine Learning
Download
13
Deep Learning - Lecture 4.2 (Deep Neural Networks II: Activation Functions)
Tübingen Machine Learning
Download
14
Deep Learning - Lecture 4.3 (Deep Neural Networks II: Preprocessing and Initialization)
Tübingen Machine Learning
Download
15
Deep Learning - Lecture 5.1 (Regularization: Parameter Penalties)
Tübingen Machine Learning
Download
16
Deep Learning - Lecture 5.2 (Regularization: Early Stopping)
Tübingen Machine Learning
Download
17
Deep Learning - Lecture 5.3 (Regularization: Ensemble Methods)
Tübingen Machine Learning
Download
18
Deep Learning - Lecture 5.4 (Regularization: Dropout)
Tübingen Machine Learning
Download
19
Deep Learning - Lecture 5.5 (Regularization: Data Augmentation)
Tübingen Machine Learning
Download
20
Deep Learning - Lecture 6.1 (Optimization: Optimization Challenges)
Tübingen Machine Learning
Download
21
Deep Learning - Lecture 6.2 (Optimization: Optimization Algorithms)
Tübingen Machine Learning
Download
22
Deep Learning - Lecture 6.3 (Optimization: Optimization Strategies)
Tübingen Machine Learning
Download
23
Deep Learning - Lecture 6.4 (Optimization: Debugging Strategies)
Tübingen Machine Learning
Download
24
Deep Learning - Lecture 7.1 (Convolutional Neural Networks: Convolution)
Tübingen Machine Learning
Download
25
Deep Learning - Lecture 7.2 (Convolutional Neural Networks: Downsampling)
Tübingen Machine Learning
Download
26
Deep Learning - Lecture 7.3 (Convolutional Neural Networks: Upsampling)
Tübingen Machine Learning
Download
27
Deep Learning - Lecture 7.4 (Convolutional Neural Networks: Architectures)
Tübingen Machine Learning
Download
28
Deep Learning - Lecture 7.5 (Convolutional Neural Networks: Visualization)
Tübingen Machine Learning
Download
29
Deep Learning - Lecture 8.1 (Sequence Models: Recurrent Networks)
Tübingen Machine Learning
Download
30
Deep Learning - Lecture 8.2 (Sequence Models: Recurrent Network Applications)
Tübingen Machine Learning
Download
31
Deep Learning - Lecture 8.3 (Sequence Models: Gated Recurrent Networks)
Tübingen Machine Learning
Download
32
Deep Learning - Lecture 8.4 (Sequence Models: Autoregressive Models)
Tübingen Machine Learning
Download
33
Deep Learning - Lecture 9.1 (Natural Language Processing: Language Models)
Tübingen Machine Learning
Download
34
Deep Learning - Lecture 9.2 (Natural Language Processing: Traditional Language Models)
Tübingen Machine Learning
Download
35
Deep Learning - Lecture 9.3 (Natural Language Processing: Neural Language Models)
Tübingen Machine Learning
Download
36
Deep Learning - Lecture 9.4 (Natural Language Processing: Neural Machine Translation)
Tübingen Machine Learning
Download
37
Deep Learning - 10.1 (Graph Neural Networks: Machine Learning on Graphs)
Tübingen Machine Learning
Download
38
Deep Learning - 10.2 (Graph Neural Networks: Graph Convolution Filters)
Tübingen Machine Learning
Download
39
Deep Learning - 10.3 (Graph Neural Networks: Graph Convolution Networks)
Tübingen Machine Learning
Download
40
Deep Learning - Lecture 11.1 (Autoencoders: Latent Variable Models)
Tübingen Machine Learning
Download
41
Deep Learning - Lecture 11.2 (Autoencoders: Principal Component Analysis
Tübingen Machine Learning
Download
42
Deep Learning - Lecture 11.3 (Autoencoders: Autoencoders)
Tübingen Machine Learning
Download
43
Deep Learning - Lecture 11.4 (Autoencoders: Variational Autoencoders)
Tübingen Machine Learning
Download
44
Deep Learning - Lecture 12.1 (Generative Adversarial Networks: Generative Adversarial Networks)
Tübingen Machine Learning
Download
45
Deep Learning - Lecture 12.2 (Generative Adversarial Networks: GAN Developments)
Tübingen Machine Learning
Download
46
Deep Learning - Lecture 12.3 (Generative Adversarial Networks: Research at AVG)
Tübingen Machine Learning
Download