Foundations of Deep Learning

Deep learning is one of the fastest growing and most exciting fields. This course will provide you with a clear understanding of the fundamentals of deep learning including the foundations to neural network architectures and learning techniques, and everything in between.

Course Overview

The course will be taught in english and will follow a flipped classroom approach.

Every week there will be:
- a video lecture
- an exercise sheet
- a flipped classroom session (live, digitally)

At the end, there will be a written exam (likely on-site).

Exercises must be completed in groups and must be submitted a week after their release. Your submissions will be graded and you will receive weekly feedback. Your final grade will be solely based on a written examination, however a passing grade for the exercises is a precondition to participate in the written exam.

The following are the PRELIMINARY dates for the release of video lectures/exercise sheets:

02.11.20 - Week 1: Overview of Deep Learning
09.11.20 - Week 2: From Logistic Regression to MLPs
16.11.20 - Week 3: Backpropagation
23.11.20 - Week 4: Optimization
30.11.20 - Week 5: Regularization
07.12.20 - Week 6: Convolutional Neural Networks (CNNs)
14.12.20 - Week 7: Recurrent Neural Networks (RNNs)
04.01.21 - Week 8: Practical Methodology & Architectures
11.01.21 - Week 9: Hyperparameter Optimization
18.01.21 - Week 10: Neural Architecture Search
25.01.21 - Week 11: Uncertainty in Deep Learning
02.02.21 - Week 12: Auto-Encoders, Variational Auto-Encoders, GANs