Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
api
on Dec 6, 2020
|
parent
|
context
|
favorite
| on:
Every Model Learned by Gradient Descent Is Approxi...
Another thought: are neural nets just a weird analog / floating point kind of probabilistic data structure or lossy compression algorithm?
Consider applying for YC's Spring batch! Applications are open till Feb 11.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
