Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
williamtrask
on March 21, 2017
|
parent
|
context
|
favorite
| on:
Deep Learning without Backpropagation
in the paper, it seemed to work quite well for LSTMS (language modeling), although it is best suited for tasks with very, very large neural networks for which parallelism is beneficial
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
