Universität Wien

300052 SE Machine Learning in Genetics (2024S)

3.00 ECTS (2.00 SWS), SPL 30 - Biologie
Prüfungsimmanente Lehrveranstaltung
VOR-ORT
Moodle
Di 07.05. 11:30-13:00 Seminarraum 1.1 PC, Biologie Djerassiplatz 1, 1.003, Ebene 1

An/Abmeldung

Hinweis: Ihr Anmeldezeitpunkt innerhalb der Frist hat keine Auswirkungen auf die Platzvergabe (kein "first come, first served").

Details

max. 12 Teilnehmer*innen
Sprache: Englisch

Lehrende

Termine (iCal) - nächster Termin ist mit N markiert

Dienstag 05.03. 11:30 - 13:00 Seminarraum 1.1 PC, Biologie Djerassiplatz 1, 1.003, Ebene 1
Dienstag 19.03. 11:30 - 13:00 Seminarraum 1.1 PC, Biologie Djerassiplatz 1, 1.003, Ebene 1
Dienstag 09.04. 11:30 - 13:00 Seminarraum 1.1 PC, Biologie Djerassiplatz 1, 1.003, Ebene 1
Dienstag 16.04. 11:30 - 13:00 Seminarraum 1.1 PC, Biologie Djerassiplatz 1, 1.003, Ebene 1
Dienstag 23.04. 11:30 - 13:00 Seminarraum 1.1 PC, Biologie Djerassiplatz 1, 1.003, Ebene 1
Dienstag 30.04. 11:30 - 13:00 Seminarraum 1.1 PC, Biologie Djerassiplatz 1, 1.003, Ebene 1
Dienstag 14.05. 11:30 - 13:00 Seminarraum 1.1 PC, Biologie Djerassiplatz 1, 1.003, Ebene 1
Dienstag 21.05. 11:30 - 13:00 Seminarraum 1.1 PC, Biologie Djerassiplatz 1, 1.003, Ebene 1
Dienstag 28.05. 11:30 - 13:00 Seminarraum 1.1 PC, Biologie Djerassiplatz 1, 1.003, Ebene 1
Dienstag 04.06. 11:30 - 13:00 Seminarraum 1.1 PC, Biologie Djerassiplatz 1, 1.003, Ebene 1
Dienstag 11.06. 11:30 - 13:00 Seminarraum 1.1 PC, Biologie Djerassiplatz 1, 1.003, Ebene 1
Dienstag 18.06. 11:30 - 13:00 Seminarraum 1.1 PC, Biologie Djerassiplatz 1, 1.003, Ebene 1
Dienstag 25.06. 11:30 - 13:00 Seminarraum 1.1 PC, Biologie Djerassiplatz 1, 1.003, Ebene 1

Information

Ziele, Inhalte und Methode der Lehrveranstaltung

• This course is designed to introduce the use of machine learning techniques in the field of population genetics. It focuses on applying these methods to analyze population genomic data.
• Participants will engage in practical problem-solving activities centered around key issues in population genetics, such as detecting introgression segments and identifying population structure. The course covers a range of machine learning paradigms including both supervised and unsupervised learning. Key models such as logistic regression, extra-trees classifiers, dimensionality reduction techniques, and artificial neural networks will be explored in detail.
• The course is structured to be highly interactive, allowing participants to apply their learning in real-time. Attendees can use their personal laptops, or the PCs provided in the lecture room for hands-on sessions.
• This course is designed for a broad audience; therefore, no prior programming experience is necessary.

Art der Leistungskontrolle und erlaubte Hilfsmittel

Two assessments are scheduled: one during session 6 and the other in session 12. These assessments will involve analysis tasks or presentations that are closely aligned with the material covered in preceding sessions.

Mindestanforderungen und Beurteilungsmaßstab

Successful completion and submission of the assigned analysis task (coding), and a scientific presentation are fundamental requirements for evaluation.
Regular attendance is mandatory to ensure a comprehensive understanding of the course material.

Prüfungsstoff

Submission of one assigned analysis task through Moodle.
Presentation of one scientific paper related to the topic (can be chosen from a list provided by the lecturers).

Literatur

• Bishop CM. 2006. Pattern Recognition and Machine Learning. Springer.
• Goodfellow I, Courville A, Bengio Y. 2016. Deep Learning. MIT Press.
• Huang X, Rymbekova A, Dolgova O, Lao O, Kuhlwilm M. 2024. Harnessing deep learning for population genetic inference. Nat Rev Genet 25: 61–78.

Zuordnung im Vorlesungsverzeichnis

MAN W5, MAN 3

Letzte Änderung: Sa 24.02.2024 18:46