Comments (9)
I think initialization will be one of the main topics that we need to study carefully and get experience on. Obvious places where we should learn from are MTP, qSNAP, pacemaker, MACE.
from acepotentials.jl.
I think the first step is to implement a one-hot initialization that will make the new models equivalent to ACE1. This is a little tricky since in the new models n
stands for the combined (n, z)
in ACE1. So I think in this case the number of n
channels must be at large enough to accomodate both n, z
.
What makes this a bit tricky is that in the regime of many or few elements the behaviour should probably be quite different...
For a first attempt my suggestion would be to choose weights such that
Rnl(rij, Zi, Zj) = Pk(rij)
where n <-> (k,z)
and the n
are assigned through a loop ordering like
n = 0
for k = 1,2,..
for z in zlist
n += 1
# ...
end
end
If we wanted to get a little more ambitious then we could assign relative weights to different elements to give higher resolution to some element-pairs than to others.
from acepotentials.jl.
Looking at pacemaker sounds something good to do.
and don't forget MTP!
Let's get something up and running and then learn from others to see how they improve...
from acepotentials.jl.
I agree it is not entirely obvious. Let's try to find time tomorrow?
from acepotentials.jl.
Looking at pacemaker sounds something good to do.
from acepotentials.jl.
I will find time to look into the one-hot in the coming week. That also give us some time to read through how others work with non-linear small MLIPs.
from acepotentials.jl.
hmm it doesn't seems to be straightforward. One probably has to allow maxn \neq maxq to proceed and this probably requires a discussion on the interface. Correct me if I am wrong?
from acepotentials.jl.
#209 goes some way towards this, but I feel this is not yet ready to be closed.
from acepotentials.jl.
I believe this is closed by #216
from acepotentials.jl.
Related Issues (20)
- Revive and redesign JSON interface HOT 3
- More graceful treatment of configs without energy labels HOT 1
- sklearn tests HOT 6
- Links to ACEfit docs HOT 1
- ACE1compat : basis mismatch HOT 1
- Getting the CI back on track HOT 1
- Purify 2B in new kernels HOT 5
- Add TRACE Variants
- Replace repulsion restraint with ZBL reference HOT 7
- Registering Next Version HOT 3
- Should Model Parameters be Unitful? HOT 1
- Accuracy Regression HOT 1
- Significant performance deterioration of basis in 0.8 HOT 1
- Shell script should offer specification of output filename HOT 9
- Smoothness Priors HOT 1
- Sparsify Potential HOT 2
- Application of Prior is Inconsistent HOT 2
- linear_errors should be renamed HOT 3
- linear_errors should be parallelized
- Constructing larger models (> 1000 basis functions) is very slow
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from acepotentials.jl.