Universität Bonn: Autonomous Intelligent SystemsInstitute for Computer Science VI: Autonomous Intelligent Systems

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

Dr. Nils Goerke

Mondays 12ct - 13:45

MA176 HS-IV

NEW Lecture Hall, Meckenheimer Alle 176, Lecture Hall IV, (2nd floor)

Re-Sit Examination:

Double check Identity and Schedule
The poll for the oral resit examination is closed.
When you are looking for a time-slot for the oral examination, please contact Dr. Nils Goerke via E-Mail.

To double check and secure your identity:

Please send an E-Mail to goerke@ais.uni-bonn.de
with Subject: TNN ResitExam

Your Name:
Your Matriculation Number:
Your E-Mail (the University Bonn e-mail preferred, starting with s6.... or s5..... )
The Day and the time slot you have chosen (to do a cross check)

For those who have not yet chosen a time slot:
please see below on this website for instructions.

For those who don't want to participate:
please send an E-Mail to me, explicitly stating this.
Thus i can arrange the time slots for the other students more easily.

Thank you for your help.

Re-Sit Examination modalities changed to Oral Exam
Due to the SARS-CoV-2 situation the risk for a written examination is considered as too high,
and thus the examination modalities have been changed.

The Re-Sit examination for the Module MA-INF 4204, Technical Neural Networks, WS19/20
will be operated as an oral exam via video-conferencing tool.

Exam Inspection via online tool:
We have organized online exam inspection via BBB tool for your TNN exam, WS19/20 by appointment. Please send an E-Mail when you are interested in such an exam inspection and we will send you a link to the BBB session:
goerke (at) ais.uni-bonn.de
Subject: TNN exam inspection
You need a camera to identify yourself by showing your student ID (Studierendenausweis) and a valid id with a photo.
You will have a timeslot of 30 minutes for the exam inspection.
Please be nice to your colleagues, and yield priority for the exam inspection for those students that participate in the oral resit examination.


Re-Sit Oral Examination, modalities and schedule:
The oral examination will take place via the video conferencing tool BigBlueButton. I will ask you a series of questions related to the lecture and the assignments of the Technical Neural Networks lecture from Wintersemester 19/20. The examination will last between 20 to 40 minutes.
You will need a video and audio connection to do the oral examination, and have a pen and some empty sheets of paper ready in case i ask you to write down a formula, or draw a sketch. During the examination i will have to see you all the time, and please ensure, that you are alone in the room during the examination time.

A doodle has been setup to arrange the exam dates, in the time from Friday 26.6.2020 to Friday 10.7.2020.
Please give your name and your E-Mail and choose the respective time slot appropriate for your examination. The doodle will not show your name to others. Please REMEMBER your time slot.
I will send you a mail with the date and time, and as soon as you have confirmed this, you will get the respective link to the examination session for the BBB tool.

The doodle poll for the resit examination is closed.
When you are looking for a time-slot for the oral examination, please contact Dr. Nils Goerke via E-Mail.


Extra Questions and Answers lecture:
On Wednesday, June 24, from 14 to 16 there will be an Extra Question and Answer Lecture for Technical Neural Networks, to prepare for the resit-examination.
Zoom-Meeting id: 930 9694 0041
Password: 1234
https://uni-bonn.zoom.us/j/93096940041?pwd=R3ZGT05VZ28rU3hsWUF5VEg0Wno0QT09
link to lecture



Starting Monday 21.Oct 2019, the lecture will be in a NEW 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 an alternative you can enter the inner court from Katzenburgweg (red pathway).

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

TNN-Exercises Homepage


Please notice: There are no prerequisites for Master of Computer Science students for this module in Winter 2019.
The lecture is organized as 2hrs lecture plus 2 hrs exercises per week.
The lecture starts on: Monday, 7 Oct 2019, 12ct, Lecture Hall 5+6, Endenicher Allee 19c.

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



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 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 admitted to the exam, you need a minimum of 50% of the points from the paper and pencil exercises and two successful presentations of your solutions within the exercise group.



Universität Bonn, Institute for Computer Science, Departments: I, II, III, IV, V, VI