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

Dr. Nils Goerke

Mondays 11:00-12:30

Lecture Hall: HS-2

Technische Neuronale Netze (4V+2Ü) (B) [B4]

Dr. Nils Goerke

Montags 11:00-12:30 und Mittwochs: 11-13

Hörsaal: HS-2

TNN-Exercises Homepage

Date for resit examination / Wiederholungsklausur

The date for the resit examination is on:
Tuesday, March 29, 2011, 10:00-12:00, Lecture hall 2
In case you have any problems with that date, please contact Dr. Nils Goerke


Termin für die Wiederholungsklausur:
Dienstag 29.März 2011, 10:00-12:00, Hörsaal 2
Wenn Sie Schwierigkeiten mit diesem Termin haben wenden Sie sich bitte sofort an Dr. Nils Goerke

Please notice: There are no prerequisites for Master of Computer Science students for this module in Winter 2010.
The lecture Technical Neural Networks, MA-INF 4204 together with the Exercises will give 6 credit points.
The lecture is organised as 2hrs lecture plus 2 hrs exercises per week in the time from Mon 11 Oct 2010 to Fr 4 Feb 2011.
The lecture starts on:Mon, 11 Oct 2010, 11:00 o'clock, Lecture Hall HS 2.
The date for the written examination will be in second week Feb 2011.

This lecture is part of the intelligent systems track of the master programme "Computer Science". It is open for CS diploma students (B)[B4].

Hinweis für Diplomstudierende

Die 4V+2Ü Vorlesung Technische Neuronale Netze (B)[B4] wird gemeinsam mit der Mastervorlesung MA-INF 4204 angeboten. Der Mischbetrieb ist wie folgend organisiert:
Vorlesung Montag: für Master MA-INF 4204 und Diplom Studierende gemeinsam.
Vorlesung Mittwoch: für Diplom Studierende.
Die aktive Teilnahme an den Übungen ist Pflicht.

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), pulse processing neural networks.

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.