At Soundtrack Your Brand we face the challenge of having to build a state-of-the-art music recommendation system, whilst not having much interactive usage data to work with. So what does it mean to build machine...
Category - Nordic Data Science and Machine Learning Summit 2021
Panel: How to leverage DataOps and MLOps to Operationalize ML and AI
Panel on How to leverage DataOps and MLOps to Operationalize ML and AI with Robert Luciani, Head of R&D at Foxrane; Hagay Lupesko, Engineering Leader at Facebook; Nishant Raj, Data & AI Strategy Lead at Atlas...
How to utilize ML in Ads – Nastaran Ghadar, Twitter
This session will be covering general techniques around how we can use ML to create better predictions in Ads impressions and also how data can be applied in targeting different user demographics and what are some of...
NLP: Big Models Aren’t Enough – Ashish Bansal, Twitch
Recent conversation in NLP has been dominated by model sizes with GPT-3 having 175B parameters. While the models are giving amazing performance, there are a number of factors beyond model size that contribute to the...
Machine Learning for Personalized Music Recommendations at Scale – Rishabh Mehrotra, Spotify
Surfacing relevant content from among millions of candidates to users in real time is a challenging task addressed by recommender systems. Modern platforms have customers not only on the demand side (e.g. users), but...
Production Machine Learning: Orchestration, Monitoring, Explainability, and Governance at Scale – Alex Housley, Seldon
Seldon CEO Alex Housley dives into how organisations can sufficiently protect their machine learning deployment through powerful monitoring capabilities. Explainability for ML algorithms is an essential companion to...
Learning Representations of Web Interfaces: Methods, Datasets and Applications – Stefan Magureanu, Klarna Bank AB
In this talk we’ll discuss methods for distilling web pages and elements into numerical representations to use as inputs to classical ML classifiers. We will look at how well different families of Graph Neural Network...
Text representations as few-shot classifiers – Melanie Beck, Cloudera
Text classification is a ubiquitous capability with a wealth of use cases. While dozens of techniques now exist for this fundamental task, many of them require massive amounts of labeled data in order to prove useful...
Building data team resilience in a turbulent world with MLOps – Shaun McGirr, Dataiku
2020 showed us the limits of a passive approach to change. Whether data teams were automating simple reports or running complex systems of machine learning models, too much changed at once to avoid significant...
Machine Learning from classification to insight challenges in production – Stephan Schwarz, Mercedes-Benz AG
The session gives an overview on some typical fields to use machine learning in production. Based on a case study (stud welding) we show typical methods like classification and root cause analysis. Further first...