Machine Learning for Multiple Domains: From Concepts to Implementation

Organized jointly by NCC Türkiye, NCC Serbia, NCC Montenegro, NCC North Macedonia

Please consider the time difference between EU countries and Türkiye. The event will start at 10:00 AM GMT+3 (09:00 CET).

Agenda: See the timetable section. 

The training will consist of the sections below: 

14 October 2024

(I) Information about the EuroCC Project and NCCs: This section covers activities such as training sessions, seminars, and conferences organised by the National Competence Centres on HPC+, along with the opportunities they offer.

Sanja Nikolic – NCC Montenegro
Prof. Boro Jakimovski – NCC North Macedonia
Dr. Dusan Vudragovic – NCC Serbia
Dr. Sezen Bostan – NCC Türkiye

(II) TRUBA Supercomputer Access: Step-by-Step Guidance from HPC Experts:

HPC Experts: Dr. Sevil Sarıkurt and Dr. İsmail Güzel

HPC experts will guide participants through accessing the TRUBA HPC infrastructure during the hands-on sessions, and participants will have the opportunity to ask questions about the infrastructure.

(III) Design, develop, deploy and iterate on production-grade ML applications 

Instructors: Prof. Dr Gjorgji Madjarov and Stefan Andonov

Skill Level: Beginner

Prerequisite: Data engineering and elementary machine learning skills

Tools, libraries, frameworks used: MLFlow, DVC, LakeFS

Learning objective: Understand the MLOps concepts and the different phases in MLOps processes and identify different levels of MLOps maturity.

Gjorgji Madjarov is a Professor at the Faculty of Computer Science and Engineering, “Ss. Cyril and Methodius” University in Skopje. His active research interests are designing advanced approaches for automated time-series modeling and forecasting, stream processing, and AI Operations using an extensive set of state-of-the-art algorithms. Building on 17 years of research, development, and management experience, he now leads a highly skilled team of professionals dedicated to delivering state-of-the-art ML solutions to the world.

Stefan Andonov is a researcher in the field of machine learning and a data engineer with several years of experience. He is currently working as a teaching and research assistant at the Faculty of Computer Science and Engineering, Ss. Cyril and Methodius University in Skopje. Additionally, he is a Data Engineering Lead at Loka, where he designs and implements data engineering and machine learning architectures for life science and healthcare companies in the USA.

(IV) Protein language models and using them for downstream prediction task

Instructors: Dr. Öznur Taştan, Zeynep Işık and Mert Pekey

Skill Level: Intermediate

Prerequisite: Basic machine learning concepts

Tools, libraries, frameworks used: Python, modules: pandas, numpy, scipy, Pytorch

Learning objective: Protein language models and how to use them in protein sequence prediction tasks

Dr. Öznur Taştan is an Associate Professor at the Faculty of Engineering and Natural Sciences of Sabanci University, affiliated with the Computer Science and Engineering and Molecular Biology Genetics and Bioengineering programs.  She obtained her Ph.D. from Language Technologies Institute, School of Computer Science, Carnegie Mellon University. She worked as a postdoctoral researcher at Microsoft Research New England. Her research lies at the intersection of computational biology and machine learning.

Zeynep Işık holds a BSc in computer engineering from Bosphorus University and is currently pursuing a master’s degree at Sabanci University. 

Mert Pekey holds a BSc degree in computer science and engineering from Sabanci University and is currently pursuing a master’s degree there.

———-

15 October 2024

(I) Modeling of large-scale social data 

Instructors: Dr. Marija Mitrović Dankulov

Skill Level: Beginner to Intermediate

Tools, libraries, frameworks used: Python, modules: pandas, numpy, scipy, networKit

Learning objective: Basic properties of social networks; how to efficiently to analyze large social networks using HPC infrastructure

Marija Mitrović Dankulov is Research Professor at Scientific Computing Laboratory and Head of Innovation Center at the Institute of physics Belgrade, the National Institute of Republic of Serbia. She completed her Ph.D. in statistical physics at the Faculty of Physics, University of Belgrade. She has extensive knowledge and experience in theoretical and computational physics. Her primary research interest is application of statistical and complex networks theory for studying socio-economic systems.

(II) Analyzing social media trends 

Instructor: Armin Alibasic

Skill Level: Beginner 

Prerequisite: Basic knowledge of Python, API connections to any of the social media

Tools, libraries, frameworks used: Python, Twitter (X) API, Vader, PySpark, NLTK, etc.

Learning objective: Participants will learn to use Python for Natural Language Processing (NLP) to analyze real-time social media data to identify trends and sentiments and provide valuable insights for business decisions.

Armin Alibasic is an Assistant Professor at the Faculty of Information Systems and Technologies at the University of Donja Gorica (UDG). He is a distinguished expert in Computer Science, specializing in Natural Language Processing (NLP) and Artificial Intelligence (AI). With a Ph.D. from Khalifa University and more than a decade of experience in Data Science and Business Analysis, Armin authored 12 scientific papers with over 140 citations, and he is the recipient of the prestigious H.H. Sheikh Mansour Bin Zayed Award for Best Research in Human Resources.

——

Contact: ncc@ulakbim.gov.tr

This course is offered free of charge

Notes:

Participants will use their own laptop or computer for the hands-on sessions.

Before the training, participants will receive instructions on how to install the software and configure the environment.

The training consists of lectures, demos, and hands-on sessions. All registered participants will be able to follow the lectures and demos; however, the hands-on sessions will have a limited capacity of 100 people (first come first served).  Participants should meet the qualification requirements (see the prerequisites above) of the hands-on sessions.  Participants (for the hands-on sessions) 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. Please make sure to provide your full name and surname correctly during registration.

Only participants from EuroHPC Joint Undertaking member institutions are eligible to attend. 

Acknowledgement

This event was supported by the EuroCC 2 and EuroCC4SEE projects. 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.

The Zoom link will only be sent to the participants who registered for the event.

Registration for this event is currently open.

Register now

More info