After successful completion of the course, students are able to: 

• understand the mathematical foundations of deep learning,
• implement and train neural networks from scratch,
• gain experience with popular deep learning frameworks (e.g., TensorFlow, PyTorch),
• develop skills to design, implement, and evaluate deep learning models for various tasks,
• understand the ethical implications and challenges associated with deep learning.

Within the last decade, deep neural networks have started to play an indispensable role in many areas of artificial intelligence including computer vision, computer graphics, natural language processing, speech recognition and robotics. 

This course provides an in-depth introduction to deep learning. Students will learn the theoretical foundations, practical implementations, and recent advancements in deep learning. Amongst other topics, we will 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, recurrent neural networks, transformers, and graph neural networks. The course will also address deep generative models such as auto-encoders, variational auto-encoders, and generative adversarial networks, as well as deep reinforcement learning, neurosymbolic approaches, and explainability. In addition, applications from various fields will be presented throughout the course. The practicals will deepen the understanding of deep neural networks by implementing and applying them in Python and PyTorch.

Lecture part with frontal lectures from April to June (16 weeks, 2 teaching hours per week).

Practicals with solving exercises and working in a team project are from April to June (16 weeks, 2 teaching hours per week):

• In week 1 to 4, you will solve exercise problems.
• In week 5 to 6, you will review TensorFlow and PyTorch tutorials during the practicals with the help of the demonstrators.
• In weeks 7 to 8, you are expected to organize in groups, and your group is expected to select a paper from the list of papers in the assessment document (which will be available on the course resources section), and prepare a work plan with a timeline, to be submitted by 6pm Friday of week 8 by email to Thomas Lukasiewicz. Each group should submit an initial plan stating your assigned group number and team members, the person in charge of submitting the presentation, the title of the paper selected, and a brief plan of action (equivalent to roughly half a side of A4).
• In weeks 9 to 15, each group is expected to reproduce the results in the selected paper, extending on the methodology and experiments.
• In week 16, each group presents their work in a presentation (with slides), and the members of each group are orally examined.

This course will be extended to 4 hours VU (= 6 ECTS): approval pending.  

Exercises have to be solved by each student individually.

ECTS Breakdown:

18h Lectures in the lecture hall
18h Exercises in the lecture hall
18h Preparation at home
18h Solving exercise problems
57h project
20h Preparation for final oral exam
  1h Presentation and final oral exam
-------------------------------------------------------------------------------
150h = 6 ECTS Total workload

Solving exercise problems, working in a team project, and presentation and oral exam at the end of the course.   

Your final grade results from your solutions to the given exercise problems, from your submitted work plan, the type of extensions made on the selected paper, the submitted slides of the presentation, the presentation itself, and the final oral exam.

Deep Learning - Goodfellow et al.

.