Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
sjg007
on Jan 30, 2017
|
parent
|
context
|
favorite
| on:
Outrageously Large Neural Networks: The Sparsely-G...
Theoretically. You can have two models Kane trained on each pathology or one model trained on examples of both in the same image. But this poses a neat mixture of experts problem instrinsic to diagnosis.
Join us for
AI Startup School
this June 16-17 in San Francisco!
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: