Deep learning

The course introduces the fundamental and current topics of deep learning.

In every weekly assignment, the students get to train a deep neural network for various tasks including image classification, machine translation, solving reasoning problems, few-shot learning and generative modeling. The course covers the most recent advances (such as unsupervised and self-supervised deep leaning) to give the student a good starting position to do research in this field.

After the course, the student

• understands the general principles of training deep neural networks (backpropagation, stochastic gradient descent, regularization)
• knows the most common neural network architectures (convolutional and recurrent neural networks, graph neural networks and transformers)
• has practical experience in implementing these models from scratch in PyTorch.

Course material

Lecture slides and lecture notes, research papers, online tutorials on PyTorch.

Teaching methods

The lectures are organised in class (voluntary). The material including the lectures will be available online. The exercises are organised via Zoom.