== Block-Seminar "Neural Networks" ==

=== General Information ===

Seminar in Neural Networks is an optional course in the module "Machine Learning 1" and is worth 3 LP (3 ECTS credits). 

||'''Erster Termin für Themenvergabe'''|| Friday, 23.10.2015, 10:00 ||
||'''Room'''|| MAR 4.033 ||
||'''Trainers'''||Gregoire Montavon ||
||'''Contact''' || gregoire.montavon@tu-berlin.de ||
||'''ISIS'''|| https://isis.tu-berlin.de/course/view.php?id=6034 ||

=== Description ===

The neural networks seminar focuses on several aspects of neural networks, including theory, modeling and algorithms. The seminar focuses on directed networks trained via backpropagation and leaves aside other types of networks such as Boltzmann machines, self-organizing maps, etc. Each student is required to choose a particular topic from a predefined list of topics (available on ISIS) and to present it at the end of the semester.