Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
dnautics
on April 6, 2017
|
parent
|
context
|
favorite
| on:
Unsupervised sentiment neuron
Is this correct? My sense from the article is that they did all the training on unsupervised, and then checked one of the recurrent lines for a correlation to sentiment, not adding a layer and doing more training.
Join us for
AI Startup School
this June 16-17 in San Francisco!
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: