inf5408 - Applied Deep Learning in PyTorch - Campusmanagementsystem Stud.IP

inf5408 - Applied Deep Learning in PyTorch

Department of Computing Science

6 KP

Module components

Semester courses Winter semester 2024/2025

Examination

Lecture

2.01.5408 - Applied Deep Learning in PyTorch
- Prof. Dr. Nils Strodthoff
- Juan Lopez Alcaraz
- Tiezhi Wang
Monday: 16:00 - 18:00, weekly (from 14/10/24), Location: A14 0-031
Dates on Monday, 17.03.2025 10:00 - 12:00, Location: A07 0-030 (Hörsaal G)
This lecture provides a comprehensive introduction to contemporary Deep Learning methods, with a specific emphasis on their practical application. Concurrently, it serves as a primer for the widely-used PyTorch Deep Learning framework, assuming only a basic familiarity with Python. The course encompasses a wide range of prevalent machine learning tasks across various data types, including tabular, image, text, audio, and graph data. Throughout the course, we delve into the most crucial and up-to-date model architectures within these domains. This encompasses convolutional neural networks, recurrent neural networks, and transformer models. The lecture is complemented by hands-on exercise sessions, where students will gain practical proficiency with PyTorch. Simultaneously, they will acquire practical insights to effectively apply contemporary deep learning methods within their specific fields of interest.

Exercises

2.01.5408a - Applied Deep Learning in PyTorch (Ü)
- Prof. Dr. Nils Strodthoff
- Tiezhi Wang
Wednesday: 16:00 - 18:00, weekly (from 16/10/24)
2.01.5408b - Applied Deep Learning in PyTorch (Ü)
- Zahra Mansour
- Prof. Dr. Nils Strodthoff
- Juan Lopez Alcaraz
Friday: 10:00 - 12:00, weekly (from 18/10/24)

Notes on the module

Prerequisites	knowledge of fundamental theoretical understanding in the field of machine learning and practical programming skills in Python.
Prüfungszeiten	at the end of the lecture period
Module examination	Written / oral exam
Skills to be acquired in this module	Professional competence The students have an overview of the components of deep learning frameworks are familiar with application areas of deep learning methods across various data modalities, and common solution strategies and model architectures can appropriately adapt deep learning methods to new problems in the respective domains and apply them independently. Methodological competence The students independently develop theoretical and practical concepts with the help of in-person events, provided materials, and specialized literature. Social competence The students can present solution approaches for problems in this area to the plenary and defend them in discussions. Self-competence The students are able to assess their own subject-specific and methodological competence take responsibility for their competence development and learning progress and reflect on these independently independently work on learning content and can critically reflect on the content.