Join the online event here

Hi AI enthusiasts! We’re thrilled to welcome to you all to another AI summit on deep learning in production (following the one with Schibstedt on the 28th). On Oct 5th, we'll be listening to Carl Thomé from Epidemic Sound and Mo Andjedani from King addressing the challenges of designing, training and deploying AI-powered systems.

We hope to see you there, or via stream!

On the agenda:

Carl Thomé, Epidemic Sound

Audio-based music similarity search with deep learning

Description: "When a YouTuber is creating a new video, they often search online for background music they can use. Traditionally this is done via search text and genre filters but a complementary interface could be to browse a catalog by providing audio examples. In this presentation, we outline the development of such a system, including the nitty gritty training of deep learning models on Google Cloud, and the deployment of an embedding serving service on Kubernetes and Elasticsearch. Expect lots of hand-wavy intuitions about self-supervised learning!"

Bio: Carl works as a machine learning engineer focused on developing ways of understanding and creating music.

Mo Andjedani, King

Challenges of productionising machine learning models: a content automation Use-case.

Content is one of the most important pillars of our games at King. Given the scale and the enormous number of players and levels, an AI-powered content automation solution is required to keep producing playful and fun-to-play levels. It has been a journey of research, experiments, development, and operations. In this talk, we will share the main challenges of ML productionisation, and how we addressed them.

Bio: Anjed is an MLOps engineer at King, as a member of the MLOps team he is improving the ml maturity level by building an end-to-end machine learning platform.

Important info

This event will be both online and physical. For those of you that have bought the ticket for the physical event you can join us in the AI Sweden office in Gallerian. If you have selected an online attendance ticket then feel free to join us using the link above!

Join the online event here