Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
whatshisface
on Nov 20, 2018
|
parent
|
context
|
favorite
| on:
Automatic Differentiation in Machine Learning: A S...
I thought the article itself did a good job of explaining it. Backpropagation is just a special case of one way to do AD, apparently. AD prescribes a method of taking derivatives, and if you use it on a neural network, there you go, backpropagation.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: