194.077 Applied Deep Learning
This course is in all assigned curricula part of the STEOP.
This course is in at least 1 assigned curriculum part of the STEOP.

2020W, VU, 2.0h, 3.0EC
TUWELQuinn ECTS survey

Properties

  • Semester hours: 2.0
  • Credits: 3.0
  • Type: VU Lecture and Exercise
  • Format: Hybrid

Learning outcomes

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

  • Understanding the principles of Deep Learning and recognize suitable problems which are solvable with Deep Learning

  • Estimate and execute the organisational tasks involved in data science projects.

  • Solving a specific research task with Deep Learning (e.g., object detetion, intelligent agents, or natural language processing).

  • Selecting a suitable Deep Learning model for the problem at hand and training it efficiently

  • Assess the found solution and present the results appropriately.

Subject of course

The focus of this course is a project, which has to be solved applying Deep Learning methods. The topic of that project can be chosen by the student. To be able to complete the project within this course, weekly lectures cover the most essential methods. Apart from an overview over Deep Learning and Neural Networks, the following advanced topics will be presented in this course and the project must use at least one of them:

  • Convolutional Neural Networks for Image Analysis

  • Recurrent Neural Networks for Sequence modeling

  • Deep Reinforcement Learning

  • Autoencoders and Deep Generative models

  • Transformers

  • Explainable AI

Additionally, practical aspects are presented throughout the course, like software libraries and frameworks, which aid the implementation process and allow to communicate the results from the project by presenting them in a meaningful way.

Teaching methods

The weekly lectures will cover the theory and applied deep learning methods, as well as practical tips to successfully realize the student project.

The project is divided into three phases that are graded separately:

  1. Selection and formulation of a suitable problem as well as procuring a suitable dataset. The goal is to find and investigate an interesting and challenging problem, for which other approaches might not work as well as Deep Learning. Students are free to choose a problem from different areas, e.g., computer vision, intelligent agents, machine translation, or audio processing. Once the problem has been formulated, a suitable dataset needs to be assembled. Depending on the question under investigation, an existing dataset can be re-used or a new dataset has to be collected.

  2. Selecting and applying a suitable model to process the dataset. In this phase, students are supposed to implement their solution. They have to select appropriate tools to efficiently train and optimize a complex model.

  3. Assessment and presentation of the solution. To assess the found solution, it has to be compared to scientific work that represents the state of the art. Finally, the project should be prepared in such a way that potential users could use it, e.g., via an API or a simple mobile application

At the end of the project, a final report has to be compiled which contains the results from those four phases. A short overview is also presented in class at the end of the semester.

Mode of examination

Immanent

Additional information

Exercises have to be solved by each student individually.

ECTS Breakdown: 3 ECTS = 75h
16h Lecture
45h Programming exercise
10h Creating the final report and the presentation
  4h Present the final results
-------------------------------------------------------------------------------
75h Total workload

For further questions regarding enrollment or the lecture itself, please contact Alexander Pacha.

Lecturers

Institute

Course dates

DayTimeDateLocationDescription
Thu16:00 - 18:0001.10.2020 - 28.01.2021 Online (LIVE)Lecture
Applied Deep Learning - Single appointments
DayDateTimeLocationDescription
Thu01.10.202016:00 - 18:00 OnlinePreliminary Lecture
Thu08.10.202016:00 - 18:00 OnlineLecture
Thu15.10.202016:00 - 18:00 OnlineLecture
Thu22.10.202016:00 - 18:00 OnlineLecture
Thu29.10.202016:00 - 18:00 OnlineLecture
Thu05.11.202016:00 - 18:00 OnlineLecture
Thu19.11.202016:00 - 18:00 OnlineLecture
Thu26.11.202016:00 - 18:00 OnlineLecture
Thu03.12.202016:00 - 18:00 OnlineLecture
Thu10.12.202016:00 - 18:00 OnlineLecture
Thu17.12.202016:00 - 18:00 OnlineLecture
Thu07.01.202116:00 - 18:00 OnlineLecture
Thu21.01.202116:00 - 18:00 OnlinePresentations
Thu28.01.202116:00 - 18:00 OnlinePresentations

Examination modalities

The proof of accomplishment consists of three parts. A software development project that investigates and attempts to solve a particular problem with Deep Learning, a technical report, and the presentation of the results.

The project is divided into three parts that are graded separately. Students are graded on their understanding of the underlying theory and their competence in solving a given problem independently.

The results are presented in the last two lectures.

Course registration

Begin End Deregistration end
31.08.2020 09:00 09.10.2020 09:00 16.10.2020 09:00

Precondition

The student has to be enrolled for at least one of the studies listed below

Curricula

Literature

Deep Learning - Goodfellow et al.

Previous knowledge

Taking the course Deep Learning for Visual Computing before this course is highly recommended, as it covers the fundamentals of Deep Learning (neural networks, optimization, backpropagation, etc.) in much greater depth, and applies them on a specific problem from the domain of Visual Computing.

Preceding courses

Language

English