Validate output based on user-defined algorithm #937
Unanswered
MaxMuehlbauer
asked this question in
Q&A
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
-
I have an input with size 76 and an output of size 6, where the output basically consists of:
Although the network is quite good at it from the training, there are some fixed rules, that must always apply to the output. I think when it was somehow possible to check during training that these rules apply, the training outcome would be even better.
The rules are (so you get an idea; in pseudo code):
Is it somehow possible to achieve this? Does it even make sense to you?
Beta Was this translation helpful? Give feedback.
All reactions