Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
|
imalexsk's comments
login
imalexsk
on July 3, 2024
|
parent
|
context
[–]
| on:
Trying Kolmogorov-Arnold Networks in Practice
the loss value he mentions for the KAN is ~1/5 (0.00011) of the NN loss (0.006). Could be a massive difference in an actual task with larger/complex datasets.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
