PyData Trójmiasto #25 - June Edition (GPNT)

We are very happy to welcome you to the 25th edition of our meetup before the summer break this year! This time we will have an opportunity to listen to as many as three insightful talks - to leave you full of ideas for the upcoming summer days!

When: 6th of June at 18:00
Where: Gdański Park Naukowo-Technologiczny (Trzy Lipy 3), Building C, Room FGH

Agenda:
18:00 - 18:05 - Meeting boarding
18:05 - 18:10 - A few words about PyData
18:10 - 18:50 - Bringing time sensitive applications to the mobile edge by Mateusz Mul (Open Sesame Media, Inc.)
18:50 - 19:30 - Satellite on-board data processing by Michał Affek (DAC.digital)
19:30 - 19:45 - Pizza break!
19:45 - 20:25 - Frontiers of Continual Learning by Sebastian Cygert (IDEAS NCBR)
20:25 - Networking!

About talks

Talk #1
Bringing time sensitive applications to the mobile edge - cross-carrier remote music collaboration case study

In this session we will delve into the world of ultra-low latencies. We will explore use cases that demand sub-100ms response times and shed light on why Multi-access Edge Computing (MEC) is a key enabling technology for such scenarios.

Presenting this session is Mateusz Mul, the Head of Product at Open Sesame Media, Inc., a Los Angeles-based startup. With a passion for music and technology, Mateusz has been at the forefront of MEC since 2018. He will share insights into the development of SyncStage, an SDK for ultra-fast audio communications, and its integration with MEC. Furthermore, Mateusz will provide details about their Mobile World Congress 2023 remote music collaboration demo prepared with three major mobile operators, which garnered recognition from AWS and was featured on their blog as a reference pattern for Multi-access Edge Computing.

By attending this session, you witness the real-world implementation of MEC in SyncStage tested on three different MEC platforms in 5G networks of eleven operators from around the world.

About Mateusz Mul
Mateusz Mul is the Head of Product @ Open Sesame Media, Inc, a Los Angeles-based startup working on SyncStage - an SDK for ultra-fast audio communications (https://sync-stage.com/). He is also one of the founders of move2edge sp. z o.o., a Gdańsk-based company focused on leveraging multi-access edge computing (MEC) for time-critical applications. His experience with MEC can be traced back to 2018 when he was working as a Python Developer on R&D projects at Vemco sp. z o.o. He loves funk music, Lindy Hop and folk dance.

Talk #2
Satellite on-board data processing

The topic revolves around data processing on remote a edge device. Namely, challenges related to such low-resource computing with the use of NVIDIA's Jetson platform will be presented. A brief introduction to machine learning algorithms, followed by an in depth explanation of performance optimization methods for their use with limited resources in a harsh environment.

Key points:

• types of data generated by satellites (broadly)
• edge computational devices suitable for space projects
• methods for neural network optimizations

About Michał Affek
Michał Affek is an Embedded Machine Learning Researcher at DAC.digital. He is currently enrolled in an industrial PhD programme at the Gdansk University of Technology. His main interests are remote sensing (processing done specifically on satellites), machine learning algorithms for edge devices, and parallel computing.

Talk #3
Frontiers of Continual Learning
Continual Learning is an emerging paradigm in machine learning where models learn new tasks in sequence without access to previously acquired knowledge. The key challenge in this field is addressing the problem of catastrophic forgetting of previous information. This is crucial because in many real-world scenarios, models must be able to adapt to constantly evolving data and tasks. During this presentation, I will discuss the latest developments in Continual Learning research and explain why it is an important research area of focus for us at IDEAS NCBR.

About Sebastian Cygert
Sebastian is a postdoctoral researcher at IDEAS NCBR and also an assistant professor at the Gdańsk University of Technology, where he earned his PhD. Previously, he was employed as an Applied Scientist at Amazon and contributed to projects such as the visual perception system for the autonomous robot Amazon Scout. He has extensive experience in a variety of computer science topics and has worked for Moody's Analytics on mathematical modeling. His research focuses on the real-world generalization and efficient computation of machine learning algorithms. In addition, he is collaborating with the Medical University of Gdańsk on a project aimed at early cancer diagnosis through the use of liquid biopsies.

A huge thank you to Vemco Sp. z o.o. (vemco.pl) for sponsoring pizzas!