Jülich Supercomputing Centre
PRACE Tutorial Parallel and Scalable Machine Learning
February 2020
Abstract
The course starts by teaching the basics of machine learning and data mining algorithms to understand the foundations of ''learning from data''. Then the course points to key challenges in analyzing large quantities of data sets in order to motivate the use of parallel and scalable machine learning algorithms.
Lecture 1 – Parallel and Scalable Machine Learning driven by HPC
Lecture 2 – Introduction to Machine Learning Fundamentals
Lecture 3 – Supervised Learning with a Simple Learning Model
Lecture 4 – Artificial Neural Networks (ANNs)
Lecture 5 – Introduction to Statistical Learning Theory
Lecture 6 – Validation and Regularization
Lecture 7 – Pattern Recognition Systems
Lecture 8 – Parallel and Distributed Training of ANN
Lecture 9 – Supervised Learning with Deep Learning
Lecture 10 – Unsupervised Learning – Clustering
Lecture 11 – Clustering with HPC
Lecture 12 – Introduction to Deep Reinforcement Learning
Practicals (codes and Jupyter notebooks)
No items found.
Previous teaching
