Practical Machine Learning: GPU edition
This two-day course gives a practical introduction to machine learning, the most important methods and algorithms, and ways of developing machine learning applications on CSC’s computing environment. We will cover, among other things, linear classification, nearest neighbor methods, decision trees, neural networks, and clustering. In addition we will introduce GPU-accelerated tools for large-scale machine learning.
The course consists of lectures and hands-on exercises using Python with Scikit-Learn: https://scikit-learn.org/, RAPIDS: https://rapids.ai/, and other relevant machine learning libraries. CSC's Notebooks (https://notebooks.csc.fi/) environment will be used on the first day of the course, and the Puhti-AI (https://research.csc.fi/-/puhti-1) cluster on the second day.
After the course the participants should have the skills and knowledge needed to begin applying machine learning for different tasks and utilizing the resources available at CSC for training and deploying their own implementations.
The participants are assumed to have a basic knowledge of Python. Additional training material useful for self study can be found here: https://docs.csc.fi/support/training-material/
Basic knowledge of a Linux/Unix environment will be assumed.
Markus Koskela (CSC), Mats Sjöberg (CSC)
Note that our online MOOC course "Practical Machine Learning” has largely overlapping contents, but without the GPU part: https://ssl.eventilla.com/event/xrv9M