Don't trust your models, explain them!

When:
- |
Track:
Sessions

More companies are using machine learning to improve their products and services. This is great, as we can all see the benefits of this. The big question is, however, can you trust these models? We’ve already seen some examples of failing machine learning models.
In this talk I’ll show you how to break open the black box of machine learning and get an interpretation of what machine learning models are doing. We’ll cover the following topics:

* Using explainers to uncover the structure of your model
* How to debug your model using explainers
* How to use explainers in production to help your users

By the end of the session you’ve learned what explainers are, how to use them, and what tools you can use to make them.

Willem Meints

Willem Meints

Technoloy Advocate/Microsoft AI MVP

Other sessions from: Main Track

World of Notebooks

World of Notebooks

Jupyter notebooks are great; running them in the cloud even better. But,...

Cihan Yakar Cihan Yakar
Realizar un aplicativo de lectura de medidores con POWER AI BUILDER

Realizar un aplicativo de lectura de medidores con POWER AI BUILDER

En esta sesión veremos un caso de negocio de cómo crear una aplicación con...

JORGE CASTILLO JORGE CASTILLO
Data & AI Platform Components in Azure

Data & AI Platform Components in Azure

Data & AI platform works together to make an organization data driven and...

Rahat Yasir Rahat Yasir
Enrich your Azure Search content with AI and Cognitive Skills

Enrich your Azure Search content with AI and Cognitive Skills

In this session, you will learn how to use Cognitive and Custom Skills to e...

Hugo Barona Hugo Barona
João Gonçalves João Gonçalves
Keynote

Keynote

Bringing all local communities together to share and care!...

Global AI Community Global AI Community
Keynote

Keynote

Bringing all local communities together to share and care!...

Global AI Community Global AI Community