Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
slashdave
6 months ago
|
parent
|
context
|
favorite
| on:
A new type of neural network is more interpretable
Orthogonality ensures that each weight has its own, individual importance. In a regular MLP, the weights are naturally correlated.
Join us for
AI Startup School
this June 16-17 in San Francisco!
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
