Student-Self-Service availability is currently restricted due to technical difficulties. Please accept our apologies for any inconvenience.

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.

2019W, VU, 2.0h, 3.0EC
TUWEL

Properties

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

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. In particular, this involves collecting, cleaning and managing large datasets.

  • Solving a specific research task with Deep Learning (e.g., detecting cars in images).

  • 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

  • Overview of Artificial Intelligence, Machine Learning, and Deep Learning

  • Neural Networks, Optimization via Backpropagation

  • Convolutional Neural Networks for Image Analysis

  • Recurrent Neural Networks for Sequence modeling

  • Autoencoders and Deep Generative models

  • Software libraries and practical aspects

  • Preprocessing, data augmentation, regularisation, visualisation

  • Explainable AI

Teaching methods

The weekly lectures will cover the basics of Deep Learning, as well as practical tips to successfully realize the student project.

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

  1. Selection and formulation of a suitable problem. 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, machine translation, or audio processing.

  2. Procure a suitable dataset. 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 generated.

  3. 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 optimize a complex model.

  4. 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

IMPORTANT: Please note that the registration for students in the master program Data Science starts only on October 1, 2019 as the course and this study are automatically mapped at the semester start. We ask for your understanding.

---

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 come to the preparatory meeting or contact Alexander Pacha.

Lecturers

Institute

Course dates

DayTimeDateLocationDescription
Thu16:00 - 18:0003.10.2019Seminarraum FAV 01 A (Seminarraum 183/2) Vorbesprechung
Thu16:00 - 18:0010.10.2019 - 31.10.2019Seminarraum FAV 01 A (Seminarraum 183/2) Lecture
Thu16:00 - 18:0014.11.2019 - 21.11.2019Seminarraum FAV 01 A (Seminarraum 183/2) Lecture
Thu16:00 - 18:0012.12.2019Seminarraum FAV 01 A (Seminarraum 183/2) Lecture
Thu16:00 - 18:0009.01.2020 - 30.01.2020Seminarraum FAV 01 A (Seminarraum 183/2) Lecture
Applied Deep Learning - Single appointments
DayDateTimeLocationDescription
Thu03.10.201916:00 - 18:00Seminarraum FAV 01 A (Seminarraum 183/2) Vorbesprechung
Thu10.10.201916:00 - 18:00Seminarraum FAV 01 A (Seminarraum 183/2) Lecture
Thu17.10.201916:00 - 18:00Seminarraum FAV 01 A (Seminarraum 183/2) Lecture
Thu24.10.201916:00 - 18:00Seminarraum FAV 01 A (Seminarraum 183/2) Lecture
Thu31.10.201916:00 - 18:00Seminarraum FAV 01 A (Seminarraum 183/2) Lecture
Thu14.11.201916:00 - 18:00Seminarraum FAV 01 A (Seminarraum 183/2) Lecture
Thu21.11.201916:00 - 18:00Seminarraum FAV 01 A (Seminarraum 183/2) Lecture
Thu12.12.201916:00 - 18:00Seminarraum FAV 01 A (Seminarraum 183/2) Lecture
Thu09.01.202016:00 - 18:00Seminarraum FAV 01 A (Seminarraum 183/2) Lecture
Thu16.01.202016:00 - 18:00Seminarraum FAV 01 A (Seminarraum 183/2) Lecture
Thu23.01.202016:00 - 18:00Seminarraum FAV 01 A (Seminarraum 183/2) Lecture
Thu30.01.202016:00 - 18:00Seminarraum FAV 01 A (Seminarraum 183/2) Lecture

Examination modalities

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

The project is divided into four parts that are graded separately. Students are graded on their understanding of the basics of Deep Learning and their competence in solving a given problem independently.

The results are presented in the last two lectures, as well as through a written report.

Course registration

Begin End Deregistration end
02.09.2019 09:00 11.10.2019 09:00 18.10.2019 09:00

Registration modalities

IMPORTANT: Please note that the registration for students in the master program Data Science starts only on October 1, 2019 as the course and this study are automatically mapped at the semester start. We ask for your understanding.

Application is currently locked manually.

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

Only for IT Master students

 

Language

if required in English