Neural Networks Demystified, Part 7: Overfitting, Testing, and Regularization

We've built and trained our neural network, but before we celebrate, we must be sure that our model is representative of the real world. We'll look at ways to diagnose and fix overfitting.


Supporting Code

Nate Silver's Book

Caltech Machine Learning Course

And the lecture shown

A big thank you to everyone who watched and commented, I really enjoyed the process and I'm excited to learn more and make better videos in 2015. Next video release will be on Friday, February 27.