Bilder vom Neuenheimer Feld, Heidelberg und der Universität Heidelberg

Lehrveranstaltungen
heiCO
Ressourcen	Fachschaft
Studien-FAQ	Technik-FAQ

Methods for Learning without Annotated Data

Module Description

Course	Module Abbreviation	Credit Points
BA-2010[100%\|75%]	CS-CL	6 LP
BA-2010[50%]	BS-CL	6 LP
BA-2010	AS-CL	8 LP
Master	SS-CL, SS-TAC	8 LP

Lecturer	Letitia Parcalabescu, Juri Opitz
Module Type	Vorlesung / Übung / Seminar
Language	English
First Session	27.04.2020
Time and Place	Monday, 16:15-17:45, INF 327 / SR 3 Wednesday, 14:15-15:45, INF 327 / SR 3
Commitment Period	tbd.

Comment

Lecture with hands-on exercises and coding sessions.

The course will be completely online during the COVID-19 pandemic.

Please enroll on the Moodle course. The password is communicated per email.

Prerequisite for Participation

good knowledge of statistical methods
incl. neural networks basic knowledge of linear algebra and calculus
advanced BA students or MA students

Assessment

Surpassing 70% of points from exercises to be accepted for the final exam
Passing the final exam

Description

Machine Learning algorithms (especially in Deep Learning) need large amounts of training data to perform well. However, high quality humanly annotated data is costly and sometimes impossible to collect.

In this course, we want to present an anthology of methods for coping with absent annotation in data.