Calculus on Computational Graphs: Backpropagation
Backpropagation is the key algorithm that makes training deep models computationally tractable. For modern neural networks, it can make training with gradient descent as much as...
WeiterlesenMonth: August 2015
Steve Yegge’s prediction record
I try to avoid making predictions1. It’s a no-win proposition: if you’re right, hindsight bias makes it look like you’re pointing out the obvious. And most...
WeiterlesenUnderstanding LSTM Networks
Humans don’t start their thinking from scratch every second. As you read this essay, you understand each word based on your understanding of previous words. You...
Weiterlesen
Reading postmortems
I love reading postmortems. They’re educational, but unlike most educational docs, they tell an entertaining story. I’ve spent a decent chunk of time reading postmortems at...
Weiterlesen