|
|
|
| Module code: NE3204.NAI |
|
|
2VU+2P (4 hours per week) |
|
5 |
| Semester: 2 |
| Mandatory course: yes |
Language of instruction:
English |
Assessment:
Written exam (50%), Presentation (50%)
[updated 15.06.2026]
|
NE3204.NAI (P213-0269, P213-0270) Neural Engineering, Master, SO 01.10.2025
, semester 2, mandatory course
|
60 class hours (= 45 clock hours) over a 15-week period.
The total student study time is 150 hours (equivalent to 5 ECTS credits).
There are therefore 105 hours available for class preparation and follow-up work and exam preparation.
|
Recommended prerequisites (modules):
None.
|
Recommended knowledge:
No prior machine learning is required. Students should be familiar with vector calculus and matrices, partial derivatives / chain rule, and basic probability; the remaining tools are introduced where needed.
Programming experience in Python is helpful but not required.
[updated 15.06.2026]
|
Recommended as prerequisite for:
|
Module coordinator:
Prof. Dr. Dr. Daniel Strauß |
Lecturer:
Prof. Dr. Dr. Daniel Strauß
[updated 15.06.2026]
|
Learning outcomes:
In this course, the students will develop a rigorous foundation in deep learning, learning the core models of classical machine learning (ML) and Deep Neural Networks. They will get familiarised with training methods, and architectures that underpin modern neuro-inspired artificial intelligence. The students will acquire knowledge on how to apply deep learning techniques (DLT), and moreover on their functional basis, the problems ML and DLT were designed to solve, and their respective limitations. Through hands-on learning from data source, building expressive functions from simple components, and designing inductive biases, the students will gain a coherent understanding of deep learning principles while exploring the DLT relationship to biological information processing. This course will set a foundation for further research, or practical applications in ML/DLT and neuro-inspired AI.
[updated 15.06.2026]
|
Module content:
1. Basics of Pattern Recognition
2.1. Supervised & Unsupervised Learning
2.2. Feature Extraction Models
2.3. Discriminant Measures
2.4. Discriminant Bases
2.5. Statistical Learning Theory
2. Learning & Cognitive Machines
2.1. Classification/Regression Trees, Boosting, Random Forests
2.2. Kernel Machines for Classification/Regression
2.3. Learning as Approximation Problem
2.4. Regularization in Reproducing Kernel Hilbert Spaces
2.5. Neural Networks & Deep Learning
2.6. Reinforcement Learning
2.7. Beyond Learning
3. Deep Learning
3.1 Introduction and Motivation
3.2 Neural Network Basics
3.3 Feedforward Networks, Backpropagation, and Optimization
3.4 Sequence and Generative Modeling
3.5 Attention and Representation Learning
3.6 Self-Supervised and Transfer Learning:
3.7 Reinforcement Learning
3.8 Applied Deep Learning and Computer Vision
3.9 Frontiers, Limitations, and Ethics
[updated 15.06.2026]
|
Teaching methods/Media:
Lectures and hands-on exercises
Blackboard, projector and Software
[updated 15.06.2026]
|
Recommended or required reading:
• Duda, Richard O.; Hart, Peter E.; Stock, David G.: Pattern Classification, Wiley, 2001, 2. Aufl., ISBN 978-0471056690
• Fletcher, R.: Practical Methods of Optimization, John Wiley & Sons, 1987
• Goodfellow, Ian; Bengio, Yoshua; Courville, Aaron: Deep Learning, MIT Press, 2016
• Schölkopf, B.; Smola, A.J.: Learning with Kernels: Support vector Machines, Regularization, Optimization and Beyond, MIT Press, 2002
• Sheppard, Clinton: Tree-based Machine Learning Algorithms: Decision Trees, Random Forests, and Boosting, CreateSpace Independent Publishing Platform, 2017, ISBN 978-1975860974
• Vapnik, V.N.: Statistical Learning Theory, John Wiley & Sons, 1998
• Wahba, G.: Spline Models for Observational Data, SIAM, 1990
• Ian Goodfellow, Yoshua Bengio, and Aaron Courville, Deep Learning. MIT Press, 2016. Freely available at https://www.deeplearningbook.org.
• Charu C. Aggarwal, Neural Networks and Deep Learning: A Textbook. 2nd edition, Springer, 2023
[updated 15.06.2026]
|
