|
Size: 1384
Comment:
|
← Revision 6 as of 2016-04-26 15:03:23 ⇥
Size: 956
Comment:
|
| Deletions are marked like this. | Additions are marked like this. |
| Line 1: | Line 1: |
| == Block-Seminar "Hot Topics in Machine Learning: Deep Learning" == | == Block-Seminar "Hot Topics in Machine Learning" == |
| Line 5: | Line 5: |
| ||'''Erster Termin für Themenvergabe'''|| Freitag, 17.04.2015, 10am-12pm in MAR 4.033 || ||'''Termin für Vorträge'''|| Freitag, 26.06.2015, 9am-3pm in MAR 4.033 || |
||'''Erster Termin für Themenvergabe'''|| 2/5/2016 14:00 Raum 4.033 Marchstr. || ||'''Termin für Vorträge'''|| TBA || |
| Line 8: | Line 8: |
| ||'''Dozent:''' || Dr. Wojciech Samek (wojciech.samek@hhi.fraunhofer.de) || | ||'''Dozent:''' || [[mailto:p.kindermans@tu-berlin.de | Pieter-Jan Kindermans]] || |
| Line 12: | Line 12: |
| This seminar takes a closer look at a very hot topic in machine learning: Deep Learning. | This seminar takes a closer look at a mix of hot topics in machine learning including, but not limited to: attention based models, quantum machine, deep reinforcement learning, privacy and machine learning, .... |
| Line 17: | Line 17: |
| * '''Deep Learning Overview''' * '''Deep Learning vs. Shallow Learning''' * '''How to train a DNNs (trips & tricks)''' * '''Understanding / Interpreting DNNs''' * '''DL in image classification''' * '''DL for object detection''' * '''DL in speech recognition''' * '''DL in text analysis''' * '''DL in video analysis''' * '''DL in fMRI analysis''' * '''Deep Boltzmann Machines''' * '''Recurrent Nets''' Reading material can be found here [[attachment:reading_material.pdf]] |
Block-Seminar "Hot Topics in Machine Learning"
Termine und Informationen
Erster Termin für Themenvergabe |
2/5/2016 14:00 Raum 4.033 Marchstr. |
Termin für Vorträge |
TBA |
Verantwortlich |
Prof. Dr. Klaus-Robert Müller |
Dozent: |
|
Sprache |
Englisch |
Anrechenbarkeit |
Wahlpflicht LV im Modul Maschinelles Lernen II (Informatik M.Sc.) |
This seminar takes a closer look at a mix of hot topics in machine learning including, but not limited to: attention based models, quantum machine, deep reinforcement learning, privacy and machine learning, ....
Students will read, understand, evaluate and present selected research papers on deep learning. At the end of the semester, each student will present his/her topic in a 25 min talk (+ 5 min questions) in English.
The topics of the seminar are: