Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
bilsbie
on June 2, 2023
|
parent
|
context
|
favorite
| on:
In vitro biological system of cultured brain cells...
Do they use gradient descent? Otherwise how do they train?
bhaney
on June 2, 2023
[–]
From the paper, it looks like they apply a long random stimulus when it misses the ball, and a short predictable stimulus when it doesn't. The theory is that the neurons will try to organize in a way that avoids the random stimulus.
Lapsa
on June 3, 2023
|
parent
[–]
cool. tldr appreciated
Join us for
AI Startup School
this June 16-17 in San Francisco!
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
