Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
cstrahan
on May 12, 2015
|
parent
|
context
|
favorite
| on:
Show HN: Recurrent neural net plays 'neural slime ...
My understanding is that the weights[1] were produced from a series of trials, and then persisted in the JS.
1:
http://en.wikipedia.org/wiki/Synaptic_weight
ColinDabritz
on May 12, 2015
[–]
It would be neat if you could have it know nothing, and learn from you over a series of games.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
1: http://en.wikipedia.org/wiki/Synaptic_weight