BEGIN:VCALENDAR VERSION:2.0 PRODID:-//PYVOBJECT//NONSGML Version 1//EN BEGIN:VTIMEZONE TZID:Europe/Brussels BEGIN:STANDARD DTSTART:20001029T030000 RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10 TZNAME:CET TZOFFSETFROM:+0200 TZOFFSETTO:+0100 END:STANDARD BEGIN:DAYLIGHT DTSTART:20000326T020000 RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3 TZNAME:CEST TZOFFSETFROM:+0100 TZOFFSETTO:+0200 END:DAYLIGHT END:VTIMEZONE BEGIN:VEVENT UID:20260603T194427Z - 79910@eu441a.odoo.com DTSTART;TZID=Europe/Brussels:20270115T090000 DTEND;TZID=Europe/Brussels:20270115T130000 CREATED:20260603T194427Z DESCRIPTION:Inside the b lack box of LLMs: how large language models really work\nEveryone is u sing large language models. Far fewer people understand what is actually h appening inside them. This masterclass changes that. In one intensive half -day session\, you will go beyond the surface-level familiarity with tools such as ChatGPT or Mistral and develop a rigorous understanding of the ar chitecture and training processes that make these systems work\, and why t hey sometimes do not. Whether you are a non-technical leader wanting to ma ke more informed strategic decisions\, or a technical professional looking for a solid conceptual foundation\, this session bridges the gap between high-level business utility and the underlying mechanics. You will leave k nowing not just what LLMs can do\, but how they do it\, where they might f all short\, and how to bring them into your organization responsibly and c ost-effectively.What you will learn The masterclass is structured around f our core themes. How LLMs work under the hood. You will demystify the tran sformer architecture\, understanding how attention mechanisms allow models to process context and meaning\, and how tokenization and embeddings form the "language" that machines use to interpret human text. You will also t race the full lifecycle of an LLM\, from large-scale pre-training on raw d ata through to supervised fine-tuning and reinforcement learning from huma n feedback (RLHF). Situating LLMs in the broader AI landscape. You will un derstand how LLMs fit within the wider fields of deep learning and natural language processing\, and how generative AI differs from classical predic tive systems. Limitations and critical assessment. You will learn to criti cally assess the real limitations of LLMs\, including stochasticity\, cont ext limits\, and bias\, so you can set realistic expectations for any proj ect involving these systems. Responsible adoption. You will apply a Buy vs Build vs Tune framework to determine the most [...] DTSTAMP:20260603T194427Z LOCATION:BeCentral\, Cantersteen 12\, 1000 Bruxelles\, Belgium SUMMARY:Inside the black box of LLMs: how large language models really work X-ALT-DESC;FMTTYPE=text/html:Inside the black box of LLMs: how large language models really work\nEveryone is using large language models. Far fewer people understand w hat is actually happening inside them. This masterclass changes that. In o ne intensive half-day session\, you will go beyond the surface-level famil iarity with tools such as ChatGPT or Mistral and develop a rigorous unders tanding of the architecture and training processes that make these systems work\, and why they sometimes do not. Whether you are a non-technical lea der wanting to make more informed strategic decisions\, or a technical pro fessional looking for a solid conceptual foundation\, this session bridges the gap between high-level business utility and the underlying mechanics. You will leave knowing not just what LLMs can do\, but how they do it\, w here they might fall short\, and how to bring them into your organization responsibly and cost-effectively.What you will learn The masterclass is st ructured around four core themes. How LLMs work under the hood. You will d emystify the transformer architecture\, understanding how attention mechan isms allow models to process context and meaning\, and how tokenization an d embeddings form the "language" that machines use to interpret human text . You will also trace the full lifecycle of an LLM\, from large-scale pre- training on raw data through to supervised fine-tuning and reinforcement l earning from human feedback (RLHF). Situating LLMs in the broader AI lands cape. You will understand how LLMs fit within the wider fields of deep lea rning and natural language processing\, and how generative AI differs from classical predictive systems. Limitations and critical assessment. You wi ll learn to critically assess the real limitations of LLMs\, including sto chasticity\, context limits\, and bias\, so you can set realistic expectat ions for any project involving these systems. Responsible adoption. You wi ll apply a Buy vs Build vs Tune framework to determine the most [...] END:VEVENT END:VCALENDAR