AI becomes more and more fundamental for tech companies. No matter if we talk about personalization, optimization, automation, or decision support; AI is changing the way we work in every aspect. Most people will agree that explainable AI (XAI) is a crucial component toward fulfilling the true potential of AI. And yet, the use of explainability in practice is very low.

There are multiple reasons for this. A common theme is that the bigger picture, i.e. the ML ecosystem that XAI is part of, is forgotten. Explainability is more than just using "import SHAP” in a notebook. You have to consider a wide variety of questions, including:

- How will users interact with the explanation?

- Where do you save the logs of your model so you can reproduce outputs?

- Who is responsible for the model and explanations?

This workshop will tackle these and other questions to help you consider XAIs role in the ML ecosystem, and make it easier to bring explainability into practice.

In this workshop you will:

- Learn how to use explainability methods to generate explainers

- Grasp the bigger picture: incorporate multiple perspectives in the creation of explainers

- Deploy models and explainers yourself, using Deeploy

For whom

For whom: This workshop is tailored to (lead/sr) data scientists, data engineers and ML engineers

Agenda

16:00 - Presentation: How to generate explainers

16:45 - Hands-on: deploy models and explainers in Deeploy

17:30 - Join us for a drink and chat!

About Deeploy

The journey of Deeploy started in 2020, but the ideas that ended up being the foundation for Deeploy were shaped over many years. With a growing number of ML models going to production, we believe it’s time for a solution that ensures manageable, explainable and accountable AI models.

Deeploy helps data scientists to deploy their models and makes them explainable, enabling interaction between humans and models.

Read this blog post to learn more about what we believe is truly explainable AI.