392117 Vertiefung Maschinelles Lernen (V) (WiSe 2020/2021)

Contents, comment

Aufbauend auf dem Grundlagen-Modul "Neuronale Netze und Lernen", welches die grundlegende Theorie des maschinellen Lernens sowie einige grundlegende Ansätze behandelt hat, werden in diesem Modul thematische Vertiefungen zu folgenden Themenfeldern behandelt: Repräsentationen, Transformer-Architekturen für Sequenzen, Generative Modelle (Autoregressiv und GAN), Neuronaler Computer,
Reinforcement-Lernverfahren, Ausgewählte Theorieaspekte, Learning to Learn (Meta-L, One/Few-Shot-L), Ausblick und aktuelle Trends.

Building on lecture "Neuronale Netze und Lernen" this module offers advanced methods in these topic areas: representations, sequence-to-sequence transformer architectures, generative models (autoregressive and GAN), neural computer, reinforcement learning methods, selected theory aspects, learning-to-learn (meta-L,one/few-shot L), outlook and current trends.

Übungen/Exercises
Anstelle wöchentlicher Übungsaufgaben bearbeiten Sie ein Miniprojekt, reichen ihre Ergebnisse in Form einer schriftlichen Ausarbeitung ein und stellen das Projekt an einem Übungstermin interaktiv vor (ca. 15min).
Instead of weekly exercises you work on a miniproject and submit your results in an interactive presentation (ca. 15min).

Requirements for participation, required level

Die Vorlesung wendet sich an einschlägig interessierte Studenten der Informatik, Mathematik und Linguistik im Hauptstudium. Notwendige Voraussetzungen: Vorlesung Neuronale Netze und Lernen.

The lecture adresses students of computer science, mathematics and linguistics within the master course. Prerequisite is basic background in Neural Networks and Learning, e.g. the lecture "Neuronale Netze und Lernen"

Bibliography

Ian Goodfellow, Yoshua Begio, Aaron Courville: Deep Learning, Springer
Bishop, Ch., "Pattern Recognition and Machine Learning", Springer
Sutton & Barto, "Reinforcement Learning: An Introduction", MIT Press
& weiterführende Literatur in den Themenkapiteln

External comments page

http://www.zfl.uni-bielefeld.de/studium/module/techfak/msc_isy/#vertiefung_maschinelles_lernen

Teaching staff

Dates ( Calendar view )

Frequency Weekday Time Format / Place Period  

Show passed dates >>

Subject assignments

Module Course Requirements  
39-M-Inf-VML Vertiefung Maschinelles Lernen Vertiefung Maschinelles Lernen Student information

The binding module descriptions contain further information, including specifications on the "types of assignments" students need to complete. In cases where a module description mentions more than one kind of assignment, the respective member of the teaching staff will decide which task(s) they assign the students.


Anzahl Einzelleistungen (benotet und unbenotet)
eine benotete Einzelleistung/Nr. of single exams (w/without mark): one exam
Prüfungsformen/Types of exams
Variant(e) 1:
benotete mündliche Prüfung über die Inhalte der Vorlesung
/oral exam with mark about the lecture
Variant(e) 2:
Ausarbeitung und interaktive Kurzpräsentation (15min) eines "Miniprojekts"
Durchschnittsnote aus Note für Präsentation und Ausarbeitung
Written report and interactive presentation (15min) of a miniproject. Average from presentation and report marks.

Voraussetzungen für die Vergabe von Leistungspunkten/Conditions for credits:

Variant(e) 1: Bestehen der mündlichen Prüfung ergibt 5 LP/successful oral exam yields 5 credits
Variant(e) 2: Erfolgreiches Miniprojekt-Ausarbeitung und Kurzpräsentation ergibt 5 LP/successful miniproject report and presentation yields 5 credits

E-Learning Space
E-Learning Space
Registered number: 74
This is the number of students having stored the course in their timetable. In brackets, you see the number of users registered via guest accounts.
Address:
WS2020_392117@ekvv.uni-bielefeld.de
This address can be used by teaching staff, their secretary's offices as well as the individuals in charge of course data maintenance to send emails to the course participants. IMPORTANT: All sent emails must be activated. Wait for the activation email and follow the instructions given there.
If the reference number is used for several courses in the course of the semester, use the following alternative address to reach the participants of exactly this: VST_230230419@ekvv.uni-bielefeld.de
Coverage:
40 Students to be reached directly via email
Notes:
Additional notes on the electronic mailing lists
Last update basic details/teaching staff:
Thursday, June 25, 2020 
Last update times:
Friday, September 11, 2020 
Last update rooms:
Friday, September 11, 2020 
Type(s) / SWS (hours per week per semester)
lecture (V) / 2
Language
This lecture is taught in english
Department
Faculty of Technology
Questions or corrections?
Questions or correction requests for this course?
Planning support
Clashing dates for this course
Links to this course
If you want to set links to this course page, please use one of the following links. Do not use the link shown in your browser!
The following link includes the course ID and is always unique:
https://ekvv.uni-bielefeld.de/kvv_publ/publ/vd?id=230230419
Send page to mobile
Click to open QR code
Scan QR code: Enlarge QR code
ID
230230419