talk-data.com

Talk Title: "Under the Hood of LLM"

Description: In this talk we unveil the inner workings of Large Language Models (LLMs), explore the architecture of Transformers and how chatbots and AI agents works underneath. This talk also dives into the concept of Model Context Protocol (MCP), the limitless potential that it offers and how it differs from RAG and other protocols like A2A. Join us for an in-depth look at how these powerful AI models that you already use on daily basis really work, how they process data, generate responses and redefine and push the boundaries of artificial intelligence.

Speaker/Bio: Radovan Kavicky Radovan Kavicky \| President & Principal Data Scientist @ GapData Institute https://www.linkedin.com/in/radovankavicky/ & https://radovankavicky.substack.com/

Radovan currently works as President & Principal Data Scientist at GapData Institute/GDI Institute and is an expert in XAI (Explainable AI), i.e. the field of scientific research at the intersection of mathematics and artificial intelligence, he also works as a AI Consultant (AI IXX/Dubai, UAE) for the implementation of AI and Data Science knowledge in business, economics and public administration

- in April 2025 he successfully completed the prestigious AI Connect program (nominated in 2024 as the only Slovak) under the auspices of the US Department of State (Bureau of Cyberspace and Digital Policy) and the Atlantic Council GeoTech Center\, which aims to help countries such as Slovakia transfer technology and knowledge in the field of AI towards responsible and successful implementation in public administration and the economy

- in April 2024 he was invited (keynote) to represent the CEE region and Europe as the historically first Slovak at the Global AI Show 2024 in Dubai (with 10k+ attendees one of the world's largest AI events)

- previously a member of Slovak.AI and until May 2024 also worked as Data Science & AI Evangelist at AIslovakIA - National Platform for the Development of Artificial Intelligence in Slovakia and in cooperation with MIRRI/MIRDI (Ministry of Investment\, Regional Development and Informatics of the Slovak Republic) led a mission of Slovak AI researchers at University of Cambridge

- Radovan is a member of several international and European professional and professional organizations in AI and data science\, such as: British Computer Society (Member\, #BCS)\, Slovak Economic Association (SEA)\, IEEE Computer Society (Member\, #IEEE)\, Slovak.AI (#SlovakAI)\, CLAIRE/CAIRNE\, European AI Alliance & TAILOR network\, AAAI\, EurAI\, AI4SK\, ELLIS\, AIDA

- selected lectures from past: @Global AI Show (Dubai\, 2024\, Keynote) @WeAreDevelopers (Berlin\, 2023) @TAILOR (Brussels\, 2023) @CODECON (Bratislava\, 2023\, main talk) @DATAcated (New York\, 2022) @PyData (Hamburg\, 2022) @ML Prague (2023\, 2022) @Data Science Summit (Warsaw\, 2021) @PyData (Hong Kong\, 2021) @ODSC Europe (London\, 2021) @WeAreDevelopers (WeAreDevsLIVE\, 2021) @Data Science Conference (DSG 5.0\, 2019) @H2O.ai (Prague\, 2019) @PyCon LT (PyData track\, Vilnius\, 2019) @VDSG (Linz\, 2019) @TechSummit (Bratislava\, 2017 & 2019) @PyData (Berlin\, 2017)

LinkedIn: https://www.linkedin.com/in/radovankavicky/

Registration:

@Meetup.com group's event here (https://www.meetup.com/pydata-slovakia-bratislava/events/307439940/) & @Eventbrite registration here (https://www.eventbrite.com/e/pydata-slovakia-ba-meetup-29-radovan-kavicky-under-the-hood-of-llm-tickets-1335453710999). +our event you can find also @Facebook here (https://www.facebook.com/events/2193597837725593/) and LinkedIn here (https://www.linkedin.com/events/7320847136919564288/about/).

[Disclaimer: If you just mark "going" @Facebook event we can't guarantee your seat]

Language of the event: English

PyData Bratislava [Python Data Enthusiasts and Users, Data Scientists & Statisticians of all levels from Slovakia]

-- PyData is a group for users and developers of data analysis tools to share ideas and learn from each other. We gather to discuss how best to apply Python tools, as well as those using R and Julia, to meet the evolving challenges in data management, processing, analytics, and visualization. PyData is organized by NumFOCUS.org, a 501(c)3 non-profit in the United States.

The PyData ​Code of Conduct​ governs this meetup. To discuss any issues or concerns relating to the code of conduct or the behavior of anyone at a PyData meetup, please contact the organizer or NumFOCUS Executive Director Leah Silen (+1512-222-5449; [email protected]).

Our Facebook group you can find here: https://www.facebook.com/groups/1813599648877946/

Our Twitter account here: https://twitter.com/PyDataBA

Our LinkedIn group here: https://www.linkedin.com/groups/13506080

Organizers: GapData Institute (https://www.gapdata.org/) (GDI) is a nonprofit nonpartisan research institution harnessing power of data & wisdom of economics for public good.

\|\| Data. Think. Change. \|\|

NumFOCUS (http://www.numfocus.org/) is a 501(c)(3) nonprofit that supports and promotes world-class, innovative, open source scientific computing. The mission of NumFOCUS is to promote sustainable high-level programming languages, open code development, and reproducible scientific research.

Welcome to the PyData Berlin May meetup!

We would like to welcome you all starting from 18:45. There will be food and drinks. The talks begin around 19.30.

Please provide your first and last name for the registration because this is required for the venue's entry policy. If you cannot attend, please cancel your spot so others are able to join as the space is limited.

Host: Bonial is excited to welcome you for this month's version of PyData. ************************************************************************** The Lineup for the evening

Talk 1: Beyond the Continuum: The Importance of Quantization in Deep Learning Abstract: Quantization is a process of mapping continuous values to a finite set of discrete values. It is a powerful technique that can significantly reduce the memory footprint and computational requirements of deep learning models, making them more efficient and easier to deploy on resource-constrained devices. In this talk, we will explore the different types of quantization techniques and discuss how they can be applied to deep learning models. In addition, we will cover the basics of NNCF and OpenVINO Toolkit, seeing how they collaborate to achieve outstanding performance - everything in a Jupyter Notebook, which allows you to try it at home.

Speaker: Adrian Boguszewski is an AI Software Evangelist at Intel. Adrian graduated from the Gdansk University of Technology in the field of Computer Science 7 years ago. After that, he started his career in computer vision and deep learning. As a team leader of data scientists and Android developers for the previous two years, Adrian was responsible for an application to take a professional photo (for an ID card or passport) without leaving home. He is a co-author of the LandCover.ai dataset, creator of the OpenCV Image Viewer Plugin, and a Deep Learning lecturer occasionally. His current role is to educate people about OpenVINO Toolkit. In his free time, he’s a traveler. You can also talk with him about finance, especially investments.

Talk 2: A Meat-ing of Minds Abstract: In this far wandering talk we consider the big meaty questions: What can AI learn from Neuroscience? What can Neuroscience learn from AI? Do LLMs "understand" language? What does "meaning" mean? Am I just a robot made of meat? These huge questions and more... will remain completely unanswered, but we will have a good time talking about them! AI, Neuroscience, Philosophy, Semantics. What more could you want?

Speaker: Andy Kitchen is the co-founder of Cortical Labs, a synthetic intelligence company growing live biological neurons inside computer chips and teaching them inside a matrix world. He is a 10+ year start-up veteran and turbo nerd. Beer, bad philosophy and type theory will be the death of him.

Lightning talks There will be slots for 2-3 Lightning Talks (3-5 Minutes for each). Kindly let us know if you would like to present something at the start of the meetup :)

*** NumFOCUS Code of Conduct THE SHORT VERSION Be kind to others. Do not insult or put down others. Behave professionally. Remember that harassment and sexist, racist, or exclusionary jokes are not appropriate for NumFOCUS. All communication should be appropriate for a professional audience including people of many different backgrounds. Sexual language and imagery are not appropriate. NumFOCUS is dedicated to providing a harassment-free community for everyone, regardless of gender, sexual orientation, gender identity, and expression, disability, physical appearance, body size, race, or religion. We do not tolerate harassment of community members in any form. Thank you for helping make this a welcoming, friendly community for all. If you haven't yet, please read the detailed version here: https://numfocus.org/code-of-conduct ***