6 min read
Lessons From Implementing a Neural Network From ScratchBackpropagation is simple in theory and unforgiving in practice. Here's what actually went wrong when I built one with nothing but numpy, and how gradient checking saved me.
4 posts
Backpropagation is simple in theory and unforgiving in practice. Here's what actually went wrong when I built one with nothing but numpy, and how gradient checking saved me.
The part of the job that's shrinking isn't the part most people worry about. It's not thinking that's getting outsourced — it's typing.
Stripped of the vector calculus notation, gradient descent is just a rule for guessing better. Here's the mechanical version I wish someone had shown me first.
Notes on the gap between knowing how to call a library and actually understanding what it's doing, and why I decided to close it the slow way.