Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
mark_l_watson
on Sept 30, 2017
|
parent
|
context
|
favorite
| on:
Nonlinear Computation in Deep Linear Networks
Well, that is cool and not what I would expect. That said, for practical applications make training easier using leaky-relu, tanh, etc. activation functions.
Consider applying for YC's Spring batch! Applications are open till Feb 11.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: