The Power of Knowledge Graphs and AI: A New Era for Developers and Data Scientists

Knowledge Graphs (KGs) are data structures that can capture complex relationships between concepts in a very flexible way. They excel at harmonizing huge amounts of heterogeneous data, and we can train AI models to generate embeddings of its nodes and vertices. These embeddings can be used to infer knowledge from the graph, such as when Facebook suggests friends you may know.

Ready to dive into the world of AI and Knowledge Graphs? We'll learn the technical side of these algorithms, their real-world applications, and how to overcome their limitations. We'll also explore current lines of research to combine them with LLMs. Join us to learn about the future of AI and how you can use it!

Vorkenntnisse

It's better if you have been working with ETL pipelines / data lakes / big data in general so that you're familiar with the challenges usually faced. It's also better if you have a high-level knowledge of what's going on in AI, and even better if you've already used embeddings.

However, if that's not you, it's alright! We'll explain everything :)

Lernziele

My session will provide a comprehensive understanding of KGs and their applications in AI. It will also introduce the audience to the concept of hybridizing KGs with LLMs, which is a cutting-edge area of research in AI. This knowledge will help data practitioners understand the future of this area of AI and how they can leverage it in their work. Moreover, KGs are a NoSQL area novel to many people, being a solid tool to dealing with big data.

Speaker

 

Aldan Creo
Aldan Creo studied CS in Spain, France and Switzerland, graduating as valedictorian. He completed 4 internships and was selected by Django for GSoC. He garnered recognition for leadership and academic excellence through several awards. He's also the founder of 3 associations and contributes to open-source. Currently, he works as Technology Research Specialist in AI at The Dock, Accenture’s R&D lab.

data2day-Newsletter

Ihr möchtet über die data2day
auf dem Laufenden gehalten werden?

 

Anmelden