Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
gracehopper
on Oct 5, 2014
|
parent
|
context
|
favorite
| on:
Do Deep Nets Really Need to be Deep? [pdf]
If true, this seems like a good thing. Is there any general way proposed in the paper to go from deep --> shallow while preserving the learning function?
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: