Module 39-M-Inf-DL Deep Learning

Faculty

Person responsible for module

Regular cycle (beginning)

Every winter semester

Credit points and duration

5 Credit points

For information on the duration of the modul, refer to the courses of study in which the module is used.

Competencies

Non-official translation of the module descriptions. Only the German version is legally binding.

Students are able to distinguish different key architectures for deep learning and they know the learning scenarios where these architectures can be used. The students know how to train a deep architecture, both, as with regards to the algorithmic pipeline and possible forms of implementation using modern systems. The module consists of lectures and exercise classes and includes an exam at the end of the term.

Content of teaching

The module introduces the basic concepts of deep learning, in particular different popular architectures including restricted Boltzmann machines, convolutional neural networks, stacked autoencoders (as concerns feedforward models), and long short term memory models and recursive networks (as concerns recurrent models). Different tricks for training are introduced including optimiziation schemes such as ADAM and training modi such as drop-out and training set enhancement. Popular applications such as for image recognition will be discussed. On a practical side, mostly TensorFlow will be used with Keras as API.

Recommended previous knowledge

Programming knowledge (Python or a similar language), Foundations of mathematics, foundations of machine learning (e.g., neural networks or introduction to machine learning)

Necessary requirements

Explanation regarding the elements of the module

Module structure: 1 bPr 1

Courses

Deep Learning
Type lecture
Regular cycle WiSe
Workload5 60 h (30 + 30)
LP 2 [Pr]
Deep Learning
Type exercise
Regular cycle WiSe
Workload5 60 h (30 + 30)
LP 2

Examinations

portfolio with final examination
Allocated examiner Teaching staff of the course Deep Learning (lecture)
Weighting 1
Workload 30h
LP2 1

Portfolio consisting of per default weekly exercises or programming tasks and final written exam (per default 60 minutes) or final oral exam (per default 15 minutes). The exercises are based on the content of the lecture and enable students to train and further investigate the topics. It is required that a sufficient percentage of the exercises are successfully completed (per default 50% of the total number of points which can be achieved during a semester). The final oral exam concerns both, the content of the lecture as well as the exercises.

The module is used in these degree programmes:

Degree programme Profile Recom­mended start 3 Duration Manda­tory option 4
Bioinformatics and Genome Research / Master of Science [FsB vom 30.09.2016 mit Änderungen vom 15.09.2017, 02.05.2018, 04.06.2020 und 31.03.2023] 1. o. 2. one semester Compul­sory optional subject
BioMechatronics / Master of Science [Studien- und Prüfungsordnung vom 22.12.2022] 1. o. 2. o. 3. one semester Compul­sory optional subject
Data Science / Master of Science [FsB vom 06.04.2018 mit Änderungen vom 01.07.2019, 02.03.2020, 21.03.2023 und 10.12.2024] Variante 1 3. one semester Compul­sory optional subject
Data Science / Master of Science [FsB vom 06.04.2018 mit Änderungen vom 01.07.2019, 02.03.2020, 21.03.2023 und 10.12.2024] Variante 2 3. one semester Compul­sory optional subject
Intelligent Systems / Master of Science [FsB vom 27.07.2018 mit Änderung vom 04.06.2020] 1. o. 2. o. 3. one semester Compul­sory optional subject
Informatics for the Natural Sciences / Master of Science [FsB vom 30.09.2016 mit Berichtigung vom 10.01.2017 und Änderungen vom 15.09.2017, 02.05.2018, 04.06.2020 und 31.03.2023] 1. o. 2. o. 3. one semester Compul­sory optional subject

Automatic check for completeness

The system can perform an automatic check for completeness for this module.


Legend

1
The module structure displays the required number of study requirements and examinations.
2
LP is the short form for credit points.
3
The figures in this column are the specialist semesters in which it is recommended to start the module. Depending on the individual study schedule, entirely different courses of study are possible and advisable.
4
Explanations on mandatory option: "Obligation" means: This module is mandatory for the course of the studies; "Optional obligation" means: This module belongs to a number of modules available for selection under certain circumstances. This is more precisely regulated by the "Subject-related regulations" (see navigation).
5
Workload (contact time + self-study)
SoSe
Summer semester
WiSe
Winter semester
SL
Study requirement
Pr
Examination
bPr
Number of examinations with grades
uPr
Number of examinations without grades
This academic achievement can be reported and recognised.