Module

PDF-Export
General information
Neural Networks and Deep Learning
Neural Networks and Deep Learning
MI116
Prof. Dr. Meyer, Carsten (carsten.meyer@haw-kiel.de)
Prof. Dr. Meyer, Carsten (carsten.meyer@haw-kiel.de)
Sommersemester 2020
1 Semester
In der Regel im Sommersemester
Englisch
Curricular relevance (according to examination regulations)
Study Subject Study Specialization Study Focus Module type Semester
M.Sc. - MIE - Information Engineering (PO 2022, V3) Information Technology and Systems Wahlmodul
M.Sc. - MIE - Information Engineering (PO 2022, V3) IT Security Wahlmodul
M.Sc. - MIE - Information Engineering (PO 2022, V3) Intelligent Systems Wahlmodul
Qualification outcome
Areas of Competence: Knowledge and Understanding; Use, application and generation of knowledge; Communication and cooperation; Scientific self-understanding / professionalism.
Neural Networks and Deep Learning recently have gained strong interest (Deep Learning has been considered one of 10 breakthrough technologies by the MIT Technology Review 2013). The aim of the course is to provide a fundamental understanding of important concepts, algorithms, techniques and architectures of neural networks and deep learning.

After completing the course, students should
have a basic overview over neural network and deep learning concepts, algorithms and architectures, suitable applications capabilities and limitations,
be able to apply suitable neural network and deep learning techniques to new problems,
analyze the outcome of neural network and deep learning experiments and explore potential methods to improve performance.

Since the lab work is being done in teams, the students learn to communicate in teams
about scientific contents and to express and justify their opinion about suitable problem
solutions and conclusions drawn from experiments.

The students learn to apply selected algorithms of neural networks and deep learning to given (toy and real)
problems, to analyze the results, draw conclusions and report the results in a scientific
way.
Content information
- Biological neurons
- Artificial neuron models
- Artificial neural networks: Architectures and the learning problem
- Feedforward neural networks and backpropagation
- Deep learning: Motivation and concepts
- Convolutional neural networks
- Unsupervised learning: Example autoencoders
- Recurrent neural networks: Long Short-Term Memory (LSTM) and (if time permits) Hopfield networks
- (If time permits) Advanced topics
- (If time permits) Self-organizing (Kohonen) maps
- Ian Goodfellowet al., “DeepLearning”, MIT Press, 2016
- Michael Nielsen: „NeuralNetworks andDeepLearning“, 2017
(More literature in the course)
Teaching formats of the courses
Teaching format SWS
Lehrvortrag 2
Labor 2
Workload
4 SWS
5,0 Credits
48 Hours
102 Hours
Module Examination
Method of Examination Duration Weighting wird angerechnet gem. § 11 Absatz 2 PVO Graded Remark
Übung 0 %
Klausur 120 Minutes 100 %
Miscellaneous
- strong interest in neural networks and deep learning
- conceptual and analytical skills
- mathematical skills desired (linear algebra, analysis, calculus), although not absolutely necessary
- programming skills desired (Python language), although not absolutely necessary
- ability to work with software libraries (in Python)
Especially suited for focus areas “A: Intelligent Systems” and “C: Information Technology and Systems Development”
Lecture will be offered at CAU Kiel (14 lectures during the regular semester at CAU Kiel, which is shifted with respect to the semester at Fachhochschule Kiel).
NOTE THAT THE EXAM WILL BE OFFERED DURING THE REGULAR EXAMINATION PERIOD OF CAU KIEL, WHICH IS SHIFTED WITH RESPECT TO THE EXAMINATION PERIOD OF FACHHOCHSCHULE KIEL!
Students are asked to bring their own laptops to the laboratory classes. Laboratory assignments are encouraged to be solved in teams of two or three students.
PDF-Export