Data Science & AI Code-Alongs

Two Microsoft experts teach you how to get started with Microsoft Fabric. You'll learn about common use cases, how to build Fabric into your data workflows, and get tips on how to be productive with Fabric.

Maxime, one of the world's leading thinkers in generative AI research, shows you how to fine-tune the Llama 3 LLM using Python and the Hugging Face platform.

Shingai Manjengwa, the Head of AI Education at Theoriq (ChainML Labs), will discuss the principles of responsible AI and demonstrate how they may be implemented in a world with multiple collaborating agents.

Bogdan, a Senior Software Engineer at DataCamp, takes you through the basics of programming with Java. You'll encounter core techniques like defining variables and flow control, and work through a problem involving data.

Aimée, a Learning Solutions Architect at DataCamp, takes you through how to use Claude. You'll get prompt engineering tips, see a data analysis workflow, and learn how to generate Python and SQL code with Claude.

Roie, a Staff Developer Advocate at Pinecone, shows you how to build an enterprise-quality RAG application.

In this session, Holly, a Staff Developer Advocate at Databricks, teaches you how to get started using the Databricks platform while working through an analysis of Olympics sporting data.

Andrea, a Computing Engineer at CERN, and Josep, a Data Scientist at the Catalan Tourist Board, will walk you through the steps needed to customize the open-source Mistral LLM.

Richie, a Senior Data Evangelist at DataCamp, shows you how to use the function calling features in the OpenAI API and GPT-4o to create a simple AI assistant that has a natural language interface.

Thomas, an analytics engineer at Metabase, takes you through a complete SQL data analysis project.

Join Iason, a Curriculum Manager at DataCamp, in creating a Power BI dashboard of historical information from the UEFA European Football Championship.

Michelle Conway, Lead Data Scientist at Lloyds Banking Group, will walk you through a simple machine learning example on banking data, including feature engineering, training a model, making predictions, and assessing model performance.