Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
_ibu9
on June 14, 2015
|
parent
|
context
|
favorite
| on:
What's Wrong with Deep Learning?
> I don't think your examples are good though, Max polling reduces noise. RuLU learn faster than Sigmoid or tanh.
That's not theory, that's just observation of the results. Why should we expect it to work that way?
Join us for
AI Startup School
this June 16-17 in San Francisco!
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
That's not theory, that's just observation of the results. Why should we expect it to work that way?