Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
jo_
on Sept 3, 2014
|
parent
|
context
|
favorite
| on:
A visual proof that neural nets can compute any fu...
I mentioned this in my post ("given nonlinear activations"), but you're correct to point out its importance. The combination of linear functions is always linear. Full stop. You need at least one non-linear layer to get reasonable results.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: