# What should you do when your machine learning algorithm is broken?

(written by lawrence krubner, however indented passages are often quotes). You can contact lawrence at: lawrence@krubner.com, or follow me on Twitter.

I’ve made every mistake that they mention in this lecture. Most of the lecture is devoted to diagnostics for ML, how you should act when your ML is not performing the way you expected:

### Post external references

1. 1
https://see.stanford.edu/Course/CS229/36
Source