Course Description

This course is an introduction to deep learning. It covers the basic concepts of deep learning, including the mathematical foundations of neural networks, the backpropagation algorithm, and the stochastic gradient descent method. It also covers the most important deep learning architectures, including convolutional neural networks, recurrent neural networks, and generative adversarial networks. The course will also cover the most important applications of deep learning, including image classification, image generation, image segmentation, object detection, and natural language processing. The course will also cover the some important tools for deep learning, such as PyTorch.

Credits: 4 CP
Frequency: Every semester

Prerequisites

Students should have a good understanding of linear algebra and probability theory. Students should also have a good understanding of the Python programming language.

Course Material

The course material will be available on OLAT. For registration, please visit KIS.

Lectures

1. Introduction to Deep Learning
2. Neural Networks
3. Convolutional Neural Networks
4. Recurrent Neural Networks
5. Generative Adversarial Networks
6. Image Classification
7. Image Generation
8. Image Segmentation
9. Object Detection
10. Natural Language Processing
11. PyTorch

Exercises

Exercises will be conducted in groups and are graded. Passing the exercises is a prerequisite for the exam.

Exam

There will be a written exam at the end of the semester. The exam will be based on the lecture material and the exercises.

Past Semesters

• Winter Semester 2018/19