Organized jointly by NCC Türkiye and NCC Czech Republic.
Date: September 11-13, 2023
Event Type: Training
Format: 100% online
Overview: For the past five years, the amount of transformer-based architectures has grown significantly and keeps dominating the deep learning domain nowadays. They can be considered another leap innovation that pushes the boundaries in deep neural network performance and scalability further. They have been demonstrated with the largest models using over half a trillion parameters and scaled up to thousands of GPUs.
In this course, participants learn the building blocks of transformer architectures in order to apply them to their own projects. These novel methods will be differentiated against existing methods, showing their advantages and disadvantages. Different hands-on exercises give the participants room to explore how the transformers work in different fields of application.
Agenda: 1:30- 5:30 PM GMT+3
September 11, 2023
Introduction to Transformers
Lead trainer: Georg Zitzlsberger
- Introduction and history
- DNN building blocks
- Advantages of Transformers
- Hands-On with PyTorch
- Machine Learning Lifecycle
- Q&A
--------------
September 12, 2023
Transformers for Natural Language Processing (NLP)
Lead trainer: Tuğba Taşkaya Temizel
- Architectures, self-supervising tasks
- Introduction to language models
- NLP Applications
- Hands-On
- Q&A
----------
September 13, 2023
Transformers in action and their applications in other domains
Lead trainer: Alptekin Temizel
- Transformers in other domains
- Deployment
- Optimizations
- Multi-GPU/-node with PyTorch DDP
- Q&A
Skill Level: Intermediate
Language: English
Prerequisite(s): Basic knowledge of Python. Knowledge of PyTorch is helpful but not mandatory. Basic principles of deep learning and machine learning
Tools, libraries, frameworks used: PyTorch
About the instructors
Tuğba Taşkaya Temizel is a Professor in the Data Informatics Department at the Graduate School of Informatics of Middle East Technical University (METU). She finished her Ph.D. studies in the Department of Computer Science at the University of Surrey in 2006. She is the coordinator of METU IS Data Mining Research Lab. She is also an NVIDIA DLI Certified Instructor and DLI University Ambassador. She is certified to teach “Fundamentals of Computer Vision (CV) 2.0” , “Fundamentals of Multiple Data Types (MDT)”, “Fundamentals of Natural Language Processing (NLP)”; and “Building Transformer-Based Natural Language Processing Applications”. She was on sabbatical leave at the University of Birmingham, UK between 2016 and 2017. Her research interests are deep learning, natural language processing, social media analytics, and data&information quality.
Alptekin Temizel is a Professor at the Graduate School of Informatics at the Middle East Technical University (METU). He obtained his Ph.D. from the Center for Vision, Speech and Signal Processing (CVSSP) at the University of Surrey in 2006. He serves as an Executive Board Member of the Neuroscience and Neurotechnology Center of Excellence and the METU Center for Image Analysis. He is the Principal Investigator of the Deep Learning and Computer Vision Research Lab and a Deep Learning Institute Certified Instructor and University Ambassador. Dr. Temizel frequently collaborates with and advises various companies. He was a Visiting Researcher at Microsoft MLDC-Lisbon during the summers of 2014 and 2015 and was on sabbatical leave at the University of Birmingham, UK from 2016-2017. His primary research interests include computer vision, machine learning, deep learning, and GPU computing and optimization.
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.
Contact: ncc@ulakbim.gov.tr
To register for the event, please visit the registration page.
This course is offered free of charge
Following your successful registration, you will receive webinar information approx. 1 day before the event.
Notes:
Participants will use their own laptop or computer for the hands-on session.
Before the training, participants will receive instructions on how to install the software and configure the environment.
The training consists of lectures and hands-on sessions. All registered participants will be able to follow the lectures; however, the hands-on sessions will have a limited capacity of 100 people. In case of more registrations, a brief form will be sent to the participants. Based on the submitted forms, participants will be selected by considering their experience, area of research, and qualifications. Participants should meet the qualification requirements of the hands-on sessions. Notification about acceptance will be sent within 5 days before the event. Selected participants (for the hands-on sessions), who don’t have an account on TRUBA infrastructure, will receive a temporary user account for the hands-on training.
Please note that the allocated compute time should only be used for running the hands-on examples.
If you are unable to attend, please cancel your registration as soon as possible so that others may have the opportunity to benefit from the hands-on sessions.
Please note that a certificate of attendance will be given only to participants who will follow a minimum of 70% of the whole duration of the course and will be signed in with full name.
Please consider the time difference between Czech Republic and Türkiye.
Sept 11-13, 2023 13:30 - 17:30 PM GMT+3 Ankara Türkiye
Sept 11-13, 2023 12:30 - 16:30 PM CET Prague Czech Republic
Acknowledgements
This event was supported by the EuroCC 2 project. This project has received funding from the European High-Performance Computing Joint Undertaking (JU) under grant agreement No 101101903. The JU receives support from the Digital Europe Programme and Germany, Bulgaria, Austria, Croatia, Cyprus, Czech Republic, Denmark, Estonia, Finland, Greece, Hungary, Ireland, Italy, Lithuania, Latvia, Poland, Portugal, Romania, Slovenia, Spain, Sweden, France, Netherlands, Belgium, Luxembourg, Slovakia, Norway, Türkiye, Republic of North Macedonia, Iceland, Montenegro, Serbia.
Follow us on Twitter and LinkedIn. Subscribe to our YouTube Channel
https://twitter.com/EuroCC_Turkey
https://www.linkedin.com/company/eurocc-turkey
https://www.youtube.com/channel/UC-qaWnbbTl6OPiPasUf4t8w/playlists
