Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
Scaevolus
on March 20, 2016
|
parent
|
context
|
favorite
| on:
XNOR-Net: ImageNet Classification Using Binary Con...
Going to 1-bit precision is probably overkill, but papers have shown how neural networks with 8 bits of precision and simple ALUs can give results equivalent to full FPUs.
Join us for
AI Startup School
this June 16-17 in San Francisco!
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: