-
Notifications
You must be signed in to change notification settings - Fork 1
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Potential Example #9
Conversation
now it returns both Aspec && AAspec
@zhanglw0521 I think I am done from my end - maybe you can take care some parts as we discussed? We can talk about this more tmr. And any objections on adding |
I added an alternative implementation of model = append_layers(l_basis,
get1 = WrappedFunction(t -> real.(t[1])),
dot = LinearLayer(length(B), 1) ) |
Debugging on progress...
|
I've now implemented forces and virials in a separate file |
Tests fail currently - pending debugging
my last commit now adds an example for differentiating the total energy w.r.t. model parameters. |
With this we can start doing parameter estimation on just energy |
I wouldn't think they should go in this PR or at least they should be done in other PRs that are based on this one. My last few commits just enabled the embedding of categorical basis onto the main chain. |
…ML to be discussed
Redundant file - was pushed mistakenly
initial test on the energy for multi-species
I see lot's of great activity. Let's keep in mind that we are producing an example here. I will start a new repository where we build the actual interatomic potential models. Let's brainstorm a name on ZuLIP I think a lot of what's being done here will move to that repo, and we can slim down the examples to something minimal. |
@cortner @CheukHinHoJerry @YangshuaiWang May I merge this PR to |
yes please go ahead. |
cc @zhanglw0521 @CheukHinHoJerry