Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
Fede_V
on May 12, 2015
|
parent
|
context
|
favorite
| on:
Keras: Fast Deep Learning Prototyping for Python
Have you taken a look at this ?
https://github.com/HIPS/autograd
and paper
http://arxiv.org/pdf/1502.03492.pdf
They reverse the computation of the gradient to calculate the derivative wrt the hyper parameters.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
They reverse the computation of the gradient to calculate the derivative wrt the hyper parameters.