Don't trust your models, explain them!
- - |
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.