Applied Deep Learning in EngineeringModule description #51077 / Version 2
- 6 CP
- Portfolio examination
- Graded
- Winter semester
- English
| Module / Version | #51077 / #2 |
|---|---|
| Validity | Since Winter semester 2025/26 |
| Available language(s) | English, German |
| Credit points | 6 |
| Person responsible for the module | Stender, Merten |
| Grading | Graded |
| Exam format | Portfolio examination |
| Language(s) of instruction | English |
Affiliation
| Faculty | Fakultät V |
|---|---|
| Institute | Institut für Maschinenkonstruktion und Systemtechnik (IMS) |
| Academic chair | 35352200 FG Cyber-Physical-Systems in Mechanical Engineering |
Contact
| Office | H 66 |
|---|---|
| Contact person | Stender, Merten |
| E-mail address | merten.stender@tu-berlin.de |
| Website | https://www.tu.berlin/cpsme |
Learning outcomes
Engineering disciplines now widely use machine learning and deep learning for system monitoring, fault detection, data-driven decision support, and harnessing big data opportunities. This module teaches advanced deep learning concepts and their implementation in Python using standard libraries. Real-world engineering examples are utilized to enhance understanding of crucial concepts in feed-forward, convolutional, and recurrent deep neural networks, including sequence classification, image classification, and object recognition. In addition, the fundamentals of reinforcement learning and generative AI methods are covered.
Upon successful completion of the module, students will acquire the following:
Knowledge:
- Advanced understanding of supervised deep learning methods, including their structure and functionality.
- Familiarity with error backpropagation, various optimization algorithms, and their unique characteristics.
- Proficiency in the architectural design and conception of deep learning methods.
- Knowledge of essential neural training parameters, regularization techniques, and training strategies.
Skills:
- Statistical characterization and evaluation of large, high-dimensional datasets.
- Handling unstructured data using convolutional and recurrent neural networks.
- Effective visualization of extensive, high-dimensional datasets.
- Implementation of core operations and key neural architectures from scratch.
- Utilization of popular programming libraries in Python.
Competencies:
- Exploratory analysis of extensive unstructured datasets.
- Feature engineering for sequential data and transformation into structured formats.
- Selection of appropriate deep learning neural architectures for structured and unstructured data.
- Evaluation of generalisation properties, under- and overfitting
- Evaluation of predictions, strengths, and weaknesses of neural learning models.
- Assessment of risks, environmental impact, and technological implications.
The course focuses 60% on knowledge & understanding, 20% on analysis & methodology, and 20% on programming.
Upon successful completion of the module, students will acquire the following:
Knowledge:
- Advanced understanding of supervised deep learning methods, including their structure and functionality.
- Familiarity with error backpropagation, various optimization algorithms, and their unique characteristics.
- Proficiency in the architectural design and conception of deep learning methods.
- Knowledge of essential neural training parameters, regularization techniques, and training strategies.
Skills:
- Statistical characterization and evaluation of large, high-dimensional datasets.
- Handling unstructured data using convolutional and recurrent neural networks.
- Effective visualization of extensive, high-dimensional datasets.
- Implementation of core operations and key neural architectures from scratch.
- Utilization of popular programming libraries in Python.
Competencies:
- Exploratory analysis of extensive unstructured datasets.
- Feature engineering for sequential data and transformation into structured formats.
- Selection of appropriate deep learning neural architectures for structured and unstructured data.
- Evaluation of generalisation properties, under- and overfitting
- Evaluation of predictions, strengths, and weaknesses of neural learning models.
- Assessment of risks, environmental impact, and technological implications.
The course focuses 60% on knowledge & understanding, 20% on analysis & methodology, and 20% on programming.
Content
- Introduction to data-driven methods and their applications in engineering.
- Supervised learning and Universal Function Approximators
- Data types and data type conversion for data-driven modeling
- Deep feed-forward artificial neural networks
- Gradient descent methods, error backpropagation, and training processes
- Families of convolutional neural networks
- Families of recurrent neural networks
- Data-driven computer vision: image classification and object detection
- Evaluation and assessment of deep learning methods
- Practical examples from engineering disciplines
- Programming tasks and implementation in the Python programming language
- Risk, environmental, and technological impact assessment
- Supervised learning and Universal Function Approximators
- Data types and data type conversion for data-driven modeling
- Deep feed-forward artificial neural networks
- Gradient descent methods, error backpropagation, and training processes
- Families of convolutional neural networks
- Families of recurrent neural networks
- Data-driven computer vision: image classification and object detection
- Evaluation and assessment of deep learning methods
- Practical examples from engineering disciplines
- Programming tasks and implementation in the Python programming language
- Risk, environmental, and technological impact assessment
Module components
Compulsory area
The following courses are mandatory for this module:
| Courses | Type | Number | Frequency | Language | Hours per week | Course catalog |
|---|---|---|---|---|---|---|
| Applied Deep Learning in Engineering | Exercise | Winter and summer semester | [en] | 2 | WS 2026/27 (1) ISIS | |
| Applied Deep Learning in Engineering | Lecture | Winter and summer semester | [en] | 2 | WS 2026/27 (1) ISIS |
Courses in the course catalog
Courses created from the teaching units of this module.
Winter semester 2026/27 (2)
Applied Deep Learning in Engineering (Exercise) 1
- Applied Deep Learning in Engineering (Übung) Termingruppe 1
Applied Deep Learning in Engineering (Lecture) 1
- Applied Deep Learning in Engineering (Vorlesung) Termingruppe 1
Workload and credit points
Applied Deep Learning in Engineering (Exercise)
| Workload description | Multiplier | Hours | Total |
|---|---|---|---|
| Attendance | 15 | 2 h | 30 h |
| Pre/post processing | 15 | 3 h | 45 h |
| Deep learning project, submission, commentary | 1 | 15 h | 15 h |
| 90 h | |||
Applied Deep Learning in Engineering (Lecture)
| Workload description | Multiplier | Hours | Total |
|---|---|---|---|
| Attendance | 15 | 2 h | 30 h |
| Pre/post processing | 15 | 4 h | 60 h |
| 90 h | |||
The workload of the module adds up to 180 hours. The module therefore comprises 6 credit points.
Description of teaching and learning methods
- Lecture: Class to convey the course content and contexts as frontal teaching with many examples from practice and interactive questions.
- Exercise: practical and guided implementation of programming tasks in the programming language Python as well as exercises in small groups to deepen and apply the lecture material.
- Portfolio examination: 1) written electronic examination (50 pts), 2) submission of a trained deep learning model including a training procedure (25 pts), 3) commentary on the model and its properties in written (1 page) or video form (3min) (25 pts).
The students submit a model trained on a provided dataset. The model is then applied to a new dataset. The students also need to predict the expected performance of the model. The results of the model evaluation are communicated to the students. The commentary should relate the chosen model structure to the evaluation results.
- Exercise: practical and guided implementation of programming tasks in the programming language Python as well as exercises in small groups to deepen and apply the lecture material.
- Portfolio examination: 1) written electronic examination (50 pts), 2) submission of a trained deep learning model including a training procedure (25 pts), 3) commentary on the model and its properties in written (1 page) or video form (3min) (25 pts).
The students submit a model trained on a provided dataset. The model is then applied to a new dataset. The students also need to predict the expected performance of the model. The results of the model evaluation are communicated to the students. The commentary should relate the chosen model structure to the evaluation results.
Requirements for participation and examination
Desirable prerequisites for participation in the courses:
- Basic statistics
- Advanced analysis (partial differentiation, gradient calculation) and linear algebra (matrix and tensor multiplication, projection methods).
- Basic concepts and methods of sequential/object-oriented programming
- Proficiency in the programming language Python
- Advanced analysis (partial differentiation, gradient calculation) and linear algebra (matrix and tensor multiplication, projection methods).
- Basic concepts and methods of sequential/object-oriented programming
- Proficiency in the programming language Python
Mandatory requirements for the module examination registration:
This module has no examination requirements.
Completion of the module
| Grading | Graded |
|---|---|
| Exam format | Portfolio examination |
| Type of portfolio examination | 100 points in total |
| Language | English |
Test elements
| Name | Points/Weight | Category | Duration/Extent |
|---|---|---|---|
| Written digital exam | 50 | written | 60 |
| Submission deep learning model | 25 | practical | 30 |
| Evaluation of the submitted model | 25 | flexibel | 20 |
Duration of the module
The following number of semesters is estimated for taking and completing the module: 1 semester(s).
This module can be started in the following semesters: Winter semester.
Maximum number of participants
This module is not limited to a number of students.
Registration procedures
Registration for the examination according to AllgStuPO in Moses. Access to teaching material and registration for the course via the e-learning platform ISIS.
Recommended reading, lecture notes
Lecture notes
unavailable
Electronic lecture notes
available
Recommended literature
No recommended literature given
Assigned programs
This module version is used in the following programs:
| Program / program version | Semester(s) | Curriculum component |
|---|---|---|
| Aeronautics and Astronautics StuPO 2018 | WS 2025/26 | 1. Ingenieurwissenschaftliche Methoden › 1.4 Regelungstechnik, Elektronik und Software-Engineering |
| SS 2026 | 1. Ingenieurwissenschaftliche Methoden › 1.4 Regelungstechnik, Elektronik und Software-Engineering | |
| WS 2026/27 | 1. Ingenieurwissenschaftliche Methoden › 1.4 Regelungstechnik, Elektronik und Software-Engineering | |
| Automotive Systems Automotive Systems (M. Sc.) - StuPO 2017 | SS 2026 | Wahlpflichtbereich |
| WS 2026/27 | Wahlpflichtbereich | |
| Biomedical Engineering StuPO 2018 | WS 2025/26 | 2. Wahlpflichtmodule › 2.2 Ingenieurwissenschaftliche Vertiefungen |
| SS 2026 | 2. Wahlpflichtmodule › 2.2 Ingenieurwissenschaftliche Vertiefungen | |
| WS 2026/27 | 2. Wahlpflichtmodule › 2.2 Ingenieurwissenschaftliche Vertiefungen | |
| Computational Engineering Science (Informationstechnik im Maschinenwesen) StuPO 2018 | WS 2025/26 | 5. Ingenieurwissenschaftliche Wahlpflichtmodule › 5.5 Informationstechnik |
| SS 2026 | 5. Ingenieurwissenschaftliche Wahlpflichtmodule › 5.5 Informationstechnik | |
| WS 2026/27 | 5. Ingenieurwissenschaftliche Wahlpflichtmodule › 5.5 Informationstechnik | |
| Computational Engineering Science (Informationstechnik im Maschinenwesen) StuPO 2018 (17.01.2018) | WS 2025/26 | 1. Kernbereich 1: Informatik und Mathematik |
| SS 2026 | 1. Kernbereich 1: Informatik und Mathematik | |
| WS 2026/27 | 1. Kernbereich 1: Informatik und Mathematik | |
| Engineering Science StuPO 09.01.2012 | WS 2025/26 | 06. Schwerpunkte › 6.3 Mechatronik › Wahlpflichtmodule |
| SS 2026 | 06. Schwerpunkte › 6.3 Mechatronik › Wahlpflichtmodule | |
| Engineering Science StuPO 2007 (19.12.2007) | WS 2025/26 | 2.1 Numerik und Simulation › 2.1b Ergänzungsbereich |
| SS 2026 | 2.1 Numerik und Simulation › 2.1b Ergänzungsbereich | |
| Engineering Science StuPO 2020 | WS 2025/26 | 2.1 Numerik und Simulation › 2.1b Ergänzungsbereich |
| SS 2026 | 2.1 Numerik und Simulation › 2.1b Ergänzungsbereich | |
| WS 2026/27 | 2.1 Numerik und Simulation › 2.1b Ergänzungsbereich | |
| Engineering Science StuPO 2020 | WS 2025/26 | Wahlpflichtmodule › 6. Schwerpunkte › 6.3 Mechatronik › Wahlpflichtmodule |
| SS 2026 | Wahlpflichtmodule › 6. Schwerpunkte › 6.3 Mechatronik › Wahlpflichtmodule | |
| WS 2026/27 | Wahlpflichtmodule › 6. Schwerpunkte › 6.3 Mechatronik › Wahlpflichtmodule | |
| Industrial Engineering and Management Industrial Engineering and Management (M. Sc.) - StuPO 2015 | WS 2025/26 | Ingenieurwissenschaftliche Studienrichtungen/Engineering Majors › Informations- und Kommunikationssysteme/Information and Communication Systems (IKS) › Informations- und Kommunikationssysteme/Information and Communication Systems (Wahlpflicht/Compulsory-Elective) › Cognitive Systems |
| SS 2026 | Ingenieurwissenschaftliche Studienrichtungen/Engineering Majors › Informations- und Kommunikationssysteme/Information and Communication Systems (IKS) › Informations- und Kommunikationssysteme/Information and Communication Systems (Wahlpflicht/Compulsory-Elective) › Cognitive Systems | |
| WS 2026/27 | Ingenieurwissenschaftliche Studienrichtungen/Engineering Majors › Informations- und Kommunikationssysteme/Information and Communication Systems (IKS) › Informations- und Kommunikationssysteme/Information and Communication Systems (Wahlpflicht/Compulsory-Elective) › Cognitive Systems | |
| Mechanical Engineering StuPO 2017 | WS 2025/26 | Wahlpflichtmodule › Profilmodule › Informationstechnische und rechnergestützte Modellierung |
| SS 2026 | Wahlpflichtmodule › Profilmodule › Informationstechnische und rechnergestützte Modellierung | |
| WS 2026/27 | Wahlpflichtmodule › Profilmodule › Informationstechnische und rechnergestützte Modellierung | |
| Mechanical Engineering StuPO 2017 | WS 2025/26 | Wahlpflichtmodule › Schwerpunktmodule › Methodenorientierung › Informationstechnische und rechnerunterstützte Modellierung |
| SS 2026 | Wahlpflichtmodule › Schwerpunktmodule › Methodenorientierung › Informationstechnische und rechnerunterstützte Modellierung | |
| WS 2026/27 | Wahlpflichtmodule › Schwerpunktmodule › Methodenorientierung › Informationstechnische und rechnerunterstützte Modellierung | |
| Technomathematics Technomathematics (M. Sc.) - StuPO 2014 | WS 2025/26 | Studienrichtungen › Maschinenbau › Maschinenbau › Profilmodule |
| SS 2026 | Studienrichtungen › Maschinenbau › Maschinenbau › Profilmodule | |
| WS 2026/27 | Studienrichtungen › Maschinenbau › Maschinenbau › Profilmodule | |
| Transport Systems StuPO 2018 | WS 2025/26 | A. Grundlagen › 2. Wahlpflichtbereich › 2.3.1 Informationstechnische Grundlagen |
| SS 2026 | A. Grundlagen › 2. Wahlpflichtbereich › 2.3.1 Informationstechnische Grundlagen | |
| WS 2026/27 | A. Grundlagen › 2. Wahlpflichtbereich › 2.3.1 Informationstechnische Grundlagen | |
| Vehicle Engineering StuPO 2017 | WS 2025/26 | 2. Profilmodule › 2.3 Ingenieurtechnische Grundlagen und Methoden |
| SS 2026 | 2. Profilmodule › 2.3 Ingenieurtechnische Grundlagen und Methoden | |
| WS 2026/27 | 2. Profilmodule › 2.3 Ingenieurtechnische Grundlagen und Methoden |
Miscellaneous
Not specified