LinkedIn
Facebook
X (Twitter)
WhatsApp
Beschreibung
Get hands-on experience in applying machine learning techniques with PyTorch.
Learning Goals:
- Mastering PyTorch best practices: tensors, datasets/dataloaders, training loops, evaluation, and debugging workflows
- Improving performance and reliability: learning-rate schedules, profiling, and automated hyperparameter tuning
- Building NLP systems with PyTorch + Hugging Face
- Preparing models for real-world deployment: export with ONNX, track experiments with MLflow, and optimize with pruning/quantization
What you get
The course instruction is hybrid, which means you can participate either online via Zoom or in person in Kiel (see location listed in the dates).
This course is based on DeepLearning.AI’s “PyTorch for Deep Learning Professional Certificate” and follows a flipped classroom approach: you work through guided online material between sessions, and we use the live class time discussion, troubleshooting, and project work.
The professional certificate is taught by Laurence Moroney and focuses on building practical deep learning systems with PyTorch, including model optimization and deployment techniques used in real-world workflows.
All needed software and online course content is free.
This course is part of the opencampus.sh Machine Learning Degree. Participants of the program for the Machine Learning Degree get preferred access to this course. Find more information on the opencampus.sh Machine Learning Degree here.
What you should bring
You already have some programming knowledge and are interested in getting hands-on knowledge in how to train and use machine learning algorithms.
Also, you should bring sufficient time. During the week you will be expected to work through the assigned online course content, for which you should calculate 5-8 hours each week. With the start of your Machine Learning project (about four to five weeks into the course), you will in addition need several hours a week to work on that.
In order to receive a certificate of achievement (Leistungszertifikat/ ECTS) for this course, active participation is expected, no more than two classes may be missed, and you have to conduct a practice project in a team of 2 to 4 persons. At the end of the course the project has to be presented and a well documented project source code has to be submitted. (Certificates of attendance are not issued i n this course.)