The basics of GenAI: theory and practice
Curious about what really powers tools like ChatGPT? In this training, you’ll dive deep into the foundations of Large Language Models and gain a clear, hands-on understanding of the tech behind generative AI.
NIEUWE DATUM!
Praktische info:
Inschrijven?
- Prijs: gratis
You need to be a PhD student at a Flemish institution to enroll
Bring your laptop (fully charged)
georganiseerd door:
Leertraject
After following this course, you'll have gained:
- Fundamental insight into the inner workings of Large Language Models
- Logical understanding of specific LLM phenomena such as ‘hallucinations’
- More concrete knowledge on how LLMs are trained and further refined
- Best practices for using Generative AI to support academic research
- Concrete examples of different parts of academic research workflows which involve using LLMs
- Hands-on experience with data conversion and code generation using LLMs
Programme
Understanding the basics of Generative AI
This 2-hour lecture outlines the fundamental algorithmic structure of Large Language Models to clarify both the impressive capacities and remaining limitations of these models. It highlights why small changes in prompts can cause substantial differences in model behavior, and how LLMs can be used both with randomness or deterministically.
Best practices for using Generative AI for academic research
This workshop utilizes the insights of the morning lecture to teach best practices for using Generative AI to support academic research. Going beyond prompt engineering, it highlights effective workflows which consider both the basic limitations of LLMs as well as their versatile output formats.
Practical examples include data conversion, code generation, and various Natural Language Processing tasks such as summarization, literature review, and academic rewriting.
Lesgever/spreker
Pieter Fivez
Dr. Pieter Fivez behaalde een doctoraat in de computerlinguïstiek aan de Universiteit Antwerpen, over deep learning en semantische representaties van biomedische teksten. Momenteel werkt hij als postdoctoraal onderzoeker aan UAntwerpen. Hij coördineert er TEXTUA (Antwerp Text Mining Centre), met een divers portfolio aan state-of-the-art projecten in text mining.
Prompt Think Defend. Data en AI voor doctoraatsstudenten
Doctoraatsstudent? In deze gecureerde lessenreeks bouw je stap voor stap kennis op rond data en AI. De verschillende leermodules worden aangeboden door VAIA, in samenwerking met alle Vlaamse universiteiten, doctoral schools en diverse lesgevers. Schrijf je in voor de mailer voor updates over het programma!
Gerelateerde opleidingen
