Explainability

Explainability is a big challenge in machine learning.

I wrote a blog post about the ELI5 library and how it can be applied to NLP models.

Introducing ML customers to explainability early on can be a great way to build trust. A colleague suggests using Streamlit tools to allow customers to play with models and understand the contribution different features have had to a particular decision.


Revision #2
Created 31 March 2022 20:29:34 by James
Updated 11 February 2024 16:26:04 by James