10 January 2023
ONLINE
Europe/Prague timezone

Annotation

Using machine or deep learning to predict specific imminent events can be useful for many applications, like predicting the failure of a hard disk or unexpected downtime of a compute node. Such events can be considered anomalies that occur unexpectedly and rarely. Hence, it is a challenge to train machine and deep learning models for these due to lack of appropriate training data.

This course covers three different methods, using XGBoost, Long Short-Term Memory (LSTM), and Autoencoders. For each, detailed hands-on exercises are provided to learn how to use these methods and how to select and pre-process training data for them.

In this workshop, attendees will learn how to:

  • Use AI-based predictive maintenance to prevent failures and unplanned downtimes.
  • Identify key challenges around detecting anomalies that can lead to costly breakdowns.
  • Use time-series data to predict outcomes with XGBoost-based machine learning classification models.
  • Use an LSTM-based model to predict equipment failure.
  • Use anomaly detection with time-series autoencoders to predict failures when limited failure-example data is available.

This training will be held ONLINE and will NOT be recorded.

Level

beginner

Language

English

Prerequisites

Experience with programming in Python and basic experience in training deep neural networks.

NVIDIA developer account is needed prior to the event. Please see the section "Practicalities" below.

Tutor

Georg Zitzlsberger is a research specialist for Machine and Deep Learning at IT4Innovations. For over four years he has been certified by NVIDIA as a University Ambassador of the NVIDIA Deep Learning Institute (DLI) program. This certification allows him to offer NVIDIA DLI courses to users of IT4Innovations' HPC services. In addition, in collaboration with Bayncore, he was a trainer for Intel HPC and AI workshops and conferences carried out across Europe. He has been contributing to these events, which are held for audiences from industry and academia, for five years. Recently, he also received instructor certifications from Intel for oneAPI related courses.

                                                                 

Acknowledgments

       

The EuroCC2 project supported this event. This project has received funding from the European High-Performance Computing Joint Undertaking (JU) under grant agreement No 101101903. This project has received funding from the Ministry of Education, Youth, and Sports of the Czech Republic.

Starts
Ends
Europe/Prague
ONLINE

Registration

Registration is obligatory. Only registered participants will receive the Zoom link. This training is offered only to members from academia.

After the number of registrations has reached its maximum or the registration form has been closed, you may want to send us an email stating that you are interested to be put on the waiting list. (Vacancies may occur due to cancellations, etc.) E-mail to training@it4i.cz

Practicalities

This training will be an online event. Technical details about joining will be sent to the accepted registrants before the event. 

Before the workshop please create an NVIDIA developer account under http://courses.nvidia.com/join using the same email address as for event registration.

The recommended browser for the course is a recent version of Chrome. Please ensure your laptop will run smoothly by going to websocketstest.com. Make sure that WebSockets work for you by seeing under Environment, WebSockets is supported and Data Receive, Send and Echo Test all check Yes under WebSockets (Port 80). If there are issues with WebSockets, try updating your browser.

Capacity and Fees

The capacity is limited to 30 participants combined online and onsite.

The course is free of charge for participants from academia. Please make sure you register using your University/Institute e-mail so that we can check your eligibility. In case you are from industry please contact us so that we can monitor the interest.

Surveys
There is an open survey.