Universität Bonn: Autonomous Intelligent Systems Group  Comouter Science Institute VI: Autonomous Intelligent Systems

Technical Neural Networks (L2E4) (MA-INF 4204)

Dr. Nils Goerke

Mondays 12 - 14

Lecture Hall IV, 2nd floor

Meckenheimer Allee 176

Starting: 10.Oct 2022, 12:00. Announcements and lecture material will be distributed via eCampus.

TNN eCampus page


Please notice: There are no prerequisites for Master of Computer Science students for this module in Winter 2022.
The lecture is organized as 2hrs lecture plus 2 hrs exercises per week.

This lecture is part of the intelligent systems track of the master programme "Computer Science".


Location:

Lecture Hall IV, 2nd floor in Building Meckenheimer Allee 176, (Geozentrum University Bonn).

Enter the building from Meckenheimer Allee (blue pathway), where the Bus stop "Botanischer Garten" is. Inside the building turn right, go down the staircase to the inner court, turn left, re-enter the building, and go to the second floor to lecture Hall IV (green cricle).

As a shorter alternative you can enter the inner court from Katzenburgweg (red pathway).

route to Meckenheimer Allee 176 route to lecture hall MA176 HS-IV



Content of the Lecture:

The lecture gives an overview over the most important technical neural networks and neural paradigms.

The following topics will be explained in detail: Perceptron, multi-layer perceptron (MLP), radial-basis function nets (RBF), Hopfield nets, self organizing feature maps (SOMS, Kohonen), adaptive resonance theory (ART), learning vector quantization, recurrent networks, back-propagation of error, reinforcement learning, Q-learning, support vector machines (SVM), Neocognitron, Convolutional Neural Networks, Deep Learning.

In addition exemplary applications of neural nets will be presented and discussed: function approximation, prediction, quality control, image processing, speech processing, action planning, control of technical processes and robots.
Implementation of neural networks in hardware and software: tools, simulators, analog and digital neural hardware.


Exercises:

The exercises are arranged to intensify the work with the research topics presented in the lecture. You will get weekly paper-and-pencil assignments that are designed to be worked on in two or three person groups and completed within one week. Your results of the assignments shall be presented and discussed during the exercise group to practice and improve your oral presentation skills. The paper and pencil assignments are accompanied by small programming tasks to be completed using individually implemented programms and stat of the art simulation tools.

To be prepared for the examination you should keep track of the lecture content by doing the assignments. The exercises and the assignments are mandatory to be admitted to the exam. So, it is a good idea to actively participate in the weekly exercise groups.



University of Bonn, Institute for Computer Science, Departments: I, II, III, IV, V, VI   Impress    Data Privacy Statement