Morris Riedel Teaching 0

Teaching – Overview

Teaching Experience Adjunct Lecturer, Lecturer, Senior Lecturer or Professor University Course: Cloud Computing and Big Data – Parallel and Scalable Machine Learning and Deep Learning, School of Engineering and Natural Sciences, University of Iceland, Iceland, Fall 2018 [ MORE ] University Course: High Performance Computing – Advanced Scientific Computing, School of Engineering and Natural Sciences, University of Iceland, Iceland, Fall 2017 [ MORE ] University Course: Cloud Computing and Big Data – Internet-based Shared Computing & Data Processing, School of Engineering and Natural Sciences, University of Iceland, Iceland, Spring 2017 University Course: High Performance Computing B – High Productivity Processing...

2019-02-25 PRACE Tutorial Parallel and Scalable Machine Learning Morris Riedel 0

PRACE Tutorial – Parallel and Scalable Machine Learning

PRACE Tutorial: Parallel and Scalable Machine Learning Invited Tutorial PRACE Advanced Training Center, Juelich Supercomputing Centre, Germany 2019-02-25 – 2019-02-27 [ EVENT ] Lecture 1 – Parallel and Scalable Machine Learning driven by HPC (pdf, ~9,97 MB) Lecture 2 – Introduction to Machine Learning Fundamentals – Theory (pdf, ~12,9 MB) Lecture 3 – Introduction to Machine Learning Fundamentals – Practice (Jupyter Notebooks – request resources contacting m.riedel@morrisriedel.de) [Martin Schultz] Lecture 4 – Feed Forward Neural Networks (Jupyter Notebooks – request resources contacting m.riedel@morrisriedel.de) [Martin Schultz] Lecture 5 – Feed Forward Neural Networks (Jupyter Notebooks – request resources contacting m.riedel@morrisriedel.de) Lecture...

2019-01-21 DEEP EST Tutorial Machine Learning and Modular Supercomputing Content 0

DEEP-EST Tutorial – Machine Learning and Modular Supercomputing

DEEP-EST Tutorial – Machine Learning and Modular Supercomputing HIPEAC Conference 2019 Conference Centre, Valencia, Spain 2019-01-21 [ Event ] Abstract The fast training of traditional machine learning models and more innovative deep learning networks from increasingly growing large quantities of scientific and engineering datasets (aka ‘Big Data‘) requires high performance computing (HPC) on modern supercomputers today. HPC technologies such as those developed within the European DEEP-EST project provide innovative approaches w.r.t. processing, memory, and modular supercomputing usage during training, testing, and validation processes. Materials [ Lecture 1: Modular Supercomputing and Machine Learning – Welcome to HiPEAC Tutorial – Slides ~1.12...

Cloud-Computing-and-Big-Data-Fall-2018 0

Cloud Computing and Big Data – Course Fall 2018

Cloud Computing and Big Data – Course Fall 2018 Parallel & Scalable Machine Learning & Deep Learning 16 university lectures with additional practical lectures for hands-on exercises in context University of Iceland, School of Engineering and Natural Sciences Faculty of Industrial Engineering, Mechanical Engineering and Computer Science Fall 2018 Lecture 0 – Prologue Slides PDF (9,59 MB) Starting teaching period with Lecture 0 – Prologue of Cloud Computing & Big Data – Parallel & Scalable Machine Learning & Deep Learning Course of @Haskoli_Islands @uni_iceland today mentioning also Modular Supercomputing driven by @DEEPprojects @fzj_jsc @fz_juelich @helmholtz_de pic.twitter.com/52bmhnZNhs — Morris Riedel (@MorrisRiedel)...

ISC2018 Tutorial on Machine Learning and Data Analytics Morris Riedel 0

ISC2018 Tutorial on Machine Learning and Data Analytics

ISC2018 Tutorial on Machine Learning and Data Analytics Invited Tutorial Science, Technology, Engineering, and Mathematics (STEM) Student Day & Gala International Supercomputing Conference (ISC), Frankfurt, Germany 2018-06-27 [ Event ] [ ISC 2018 Tutorial on Machine Learning and Data Analytics – Slides ~15.4 MB (pdf) ] Thanks to the ISC 2018 @ISCHPC team for inviting me to give a HPC Machine Learning & Data Analytics tutorial at the STEM student day; nice discussions with students about modular supercomputing driven by @DEEPprojects, @fzj_jsc & @Haskoli_Islands; slides: https://t.co/xCDitaxS71 pic.twitter.com/pBQ1JXKPJU — Morris Riedel (@MorrisRiedel) June 29, 2018 Meeting many colleagues of our DEEP-EST...

2018-06-06-Introduction-To-Deep-Learning-Tutorial-Content 0

DEEP-EST Tutorial: Introduction to Deep Learning

DEEP-EST Tutorial: Introduction to Deep Learning Tutorial under the umbrella of the DEEP-EST EU Project Juelich Supercomputing Centre, Germany 2018-06-06 – 2018-06-07 [ Event ] Materials [ Lecture 1 – Introduction to Deep Learning – Slides ~3.29 MB (pdf) ] [ Lecture 2 – Fundamentals of Convolutional Neural Networks (CNNs) – Slides ~3.81 MB (pdf) ] [ Lecture 3 – Deep Learning in Remote Sensing: Challenges – Slides ~8.11 MB (pdf) ] [ Lecture 4 – Deep Learning in Remote Sensing: Applications – Slides ~1.98 MB (pdf) ] [ Lecture 5 – Model Selection and Regularization – Slides ~1.78 MB...

2018-03-06-Parallel-and-Scalable-Machine-Learning-Tutorial-Content 0

DEEP-EST Tutorial: Parallel and Scalable Machine Learning

DEEP-EST Tutorial: Parallel and Scalable Machine Learning Tutorial under the umbrella of the DEEP-EST EU Project Juelich Supercomputing Centre, Germany 2018-03-06 – 2018-03-08 [ Event ] Abstract: The course offers basics of analyzing data with machine learning and data mining algorithms in order to understand foundations of learning from large quantities of data. This course is especially oriented towards beginners that have no previous knowledge of machine learning techniques. The course consists of general methods for data analysis in order to understand clustering, classification, and regression. This includes a thorough discussion of test datasets, training datasets, and validation datasets required...

2018 Tutorial Parallel and Scalable Machine Learning 0

Tutorial: Parallel and Scalable Machine Learning

Tutorial: Parallel and Scalable Machine Learning Invited Tutorial PRACE Advanced Training Center, Juelich Supercomputing Centre, Germany 2018-01-15 – 2018-01-17 [ EVENT ] Abstract: The course offers basics of analyzing data with machine learning and data mining algorithms in order to understand foundations of learning from large quantities of data. This course is especially oriented towards beginners that have no previous knowledge of machine learning techniques. The course consists of general methods for data analysis in order to understand clustering, classification, and regression. This includes a thorough discussion of test datasets, training datasets, and validation datasets required to learn from data...

HPC-Fall-2017 0

HPC – Course Fall 2017

High Performance Computing 18 university lectures with additional practical lectures for hands-on exercises in context University of Iceland, School of Engineering and Natural Sciences Faculty of Industrial Engineering, Mechanical Engineering and Computer Science Fall 2017 Lecture 0 – Prologue Slides PDF (5,38 MB) Lecture 1 – High Performance Computing Slides PDF (3,96 MB) Lecture 2 – Parallelization Fundamentals Slides PDF (5,93 MB) Lecture 3 – Parallel Programming with MPI Slides PDF (1,83 MB) Lecture 4 – Advanced MPI Techniques Slides PDF (3,33 MB) Lecture 5 – Parallel Algorithms & Data Structures Slides PDF (3,78 MB) Lecture 6 – Parallel Programming...

2016 Tutorial Einfuehrung Maschinelles Lernen

Tutorial: Einfuehrung in Maschinelles Lernen zur Datenanalyse (2016)

TUTORIAL: Einführung in Maschinelles Lernen zur Datenanalyse Invited Tutorial (German language) Smart Data Innovation Conference, Karlsruhe Institute of Technology (KIT), Germany 2016-10-13 [ Event ] Abstract: Der Kurs vermittelt Grundlagen zur Analyse von Daten und ist an Kursbesucher gerichtet die keine Vorkenntnisse in diesem Bereich haben. Die Inhalte werden prinzipielle Techniken umfassen, um Methoden der Datenanalyse wie Clustering, Klassifikation oder Regression besser einzuordnen. Das beinhaltet auch ein Verständnis von Testdaten, Trainingsdaten und Validierungsdaten. Anhand von einfachen Beispielen werden weiterhin Probleme wie bspw. overfitting angesprochen sowie dessen Lösungsansätze Validierung und Regularisierung. Nach dem Kurs haben Teilnehmer das Verständnis wie man an...