High Performance Data Analytics - Part I

Event content

Big Data Analytics problems are ubiquitous in scientific research, industrial production and business services. Developing and maintaining efficient tools for storing, processing and analysing Big Data in powerful supercomputers is necessary for discovering patterns and gaining insights for data-intensive topics including biomolecular science, global climate change, accurate weather prediction, cancer research and cybersecurity among others. Building enough man-power (human resources) to be able to utilize the increasing computational power in High Performance Computing (HPC) infrastructure to process and analyse Big Data is of great importance in advancing Big Data Analytics and Machine Learning.

This course is divided into two parts to effectively fulfil its objectives. In the first part, learners will be provided with foundational knowledge on emerging tools for Data Analysis in HPC systems. We will investigate parallelization opportunities in standard examples of Big Data Analytics. Learners will also acquire skills on how to organize and store data in Data Lakes and Data Warehouses.

Learning goal

Providing interested learners with foundational knowledge on emerging tools for Data Analysis in HPC systems.

Information about the event

Max. participants

15

Requirements

• Course “Using the GWDG Scientific Compute Cluster – An Introduction” or general knowledge on Linux and HPC system
• Basic understanding of Linear Algebra
• Basic programming skills in Python

Speakers

Dr. Jack Ogaja

Hendrik Nolte

Tino Meisel