Adversarial neural network MCMC #1643
ben18785
started this conversation in
Ideas/Science
Replies: 2 comments
-
That's a cool idea! Might belong in the big compare-everything-with-everything project more than PINTS itself? Or do you think we need an intermediary project?
or
? |
Beta Was this translation helpful? Give feedback.
0 replies
-
Yeah, not sure. Think we'd probably want a repo for PINTS w Tensorflow
since there are increasingly more samplers that fit this category (and
something I'd like to experiment with myself!).
…On Mon, Feb 17, 2020 at 1:43 PM Michael Clerx ***@***.***> wrote:
That's a cool idea! Might belong in the big
compare-everything-with-everything project more than PINTS itself? Or do
you think we need an intermediary project?
PINTS (clean)
|
performance-testing
or
PINTS (clean)
|
PINTS w Tensorflow
|
performance-testing
?
—
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub
<#1040?email_source=notifications&email_token=ABCILKBMH6QVLKRQRHRMEOTRDKH7FA5CNFSM4KWRHST2YY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOEL6OQ4Y#issuecomment-586999923>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/ABCILKFEYFJMWSJWSDJX4XTRDKH7FANCNFSM4KWRHSTQ>
.
|
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
These train adversarial neural networks iteratively to sample from the posterior.
More widely, I think it could be good to have a PINTS branch/offshoot that depends on Tensorflow so we can include these types of samplers.
Beta Was this translation helpful? Give feedback.
All reactions