Comments (4)
Hi @sirmarcel,
Good to hear that you have had similar experiences!
I think the choice of using a polynomial kernel of the form <p, p'>^\zeta
(eq. 36 in [1]) when measuring the similarity of two environments and dubbing this the "SOAP kernel" was a bit misleading. As far as I understand, this particular kernel is not required for some special reason but is a decision made by the authors. They certainly demonstrate that the dot product corresponds to the angular integral, so it should be a good idea to base the kernel on top of it, but the polynomial kernel is not the only choice. It is partly up to the user to benchmark different kernels functions, as there might be some differences depending on the application. The Gaussian kernel (which in fact can be shown to correspond to an infinite sum of polynomials of the form <p, p'>^n
) should definitely be a valid choice as well.
[1] Albert P. Bartok, Risi Kondor, and Gabor Csanyi, On representing chemical environments, Phys. Rev. B (2013) 87, 184115
from dscribe.
Hi @bartolsthoorn!
Thank you for the great question! This is a topic that has not been so clear to me either, but I will try to illustrate my view on it here.
You are indeed right that only by taking the inner product of the power spectras you will arrive at the correct overlap of the atomic environments. This original definition of the "SOAP kernel" (=polynomial kernel) is also explicitly mentioned in our SOAP tutorial.
Nothing in practice, however, restricts using any other kernel or other machine learning method on the power spectra. I would even say that the spectrum on its own is a more useful and general concept, as it is a vector that directly describes the atomic environment (it is not just a useless intermediate step.)
We have some experience on using other kernels (see section II B in the Supplementary Information of this publication) and have noticed that e.g. the Gaussian Kernel performs at least as well for our particular application. Also, I would argue that in some cases using methods that are not based on kernels (=do not reduce the similarity to a single number), are a better fit. E.g. decision trees or neural networks may pick up on more complicated trends in the spectrum. Also, the spectra on its own can be used in other machine learning tasks, such as clustering.
Hope this helps!
from dscribe.
Hi,
(hope I'm not disturbing y'all),
Just wanted to second @lauri-codes; in our benchmarking (a paper is forthcoming), SOAP also performs extremely well with the Gaussian kernel!
I think it's perfectly valid to view SOAP as a descriptor -- it is simply a vector with the "correct" invariances (rotation, translation, etc.) and can be directly derived as such. Computing the "overlap" integral is one particular (but not the only) way of arriving at the SOAP definition, and one way to interpret the notion of "comparing" environments. There's nothing intrinsically "more" correct about it.
I also agree that using the spectrum is more convenient, and in some ways more elegant, since it separates the task of feature generation from regression, as it's usually done in ML.
Cheers!
from dscribe.
Thank you all for the insightful comments, very useful! 👍
from dscribe.
Related Issues (20)
- Is it possible to parallelize `lmbtr.create` when working on one `ase.Atoms` object? HOT 3
- Error with np.str (NumPy >= 1.24) HOT 1
- Descriptor that recognizes each atom of the same species differently HOT 1
- The example in README.md is not correct HOT 1
- [Bug] Error in SOAP derivatives when using weighting. HOT 2
- API compatibility is broken since 0696656 HOT 1
- ACSF.create cannot accept cartesian positions as "centers" parameter HOT 2
- Numpy operations on sparsed derivatives HOT 5
- Similarity based on Average kernel obtain deferent value between each atom and its replica atoms. HOT 1
- Please make dscribe available at conda-forge/osx-arm64 channel HOT 3
- SOAP computation hangs when `calc` is not `None` in ASE trajectory HOT 2
- Can dscribe encode the atom type not in the list as "unkown type" in acsf calculation? HOT 2
- Descsize of ASCF HOT 1
- conda channel has no function for features' derivatives
- `CoulombMatrix(permutation="sorted_l2")` is not symmetric HOT 5
- Naming incosistency of rcut in SOAP and MBTR HOT 2
- Potential memory leak in MBTR HOT 2
- Analytical derivatives of SOAP HOT 4
- Identical geometry but similarity < 1 HOT 4
- Numerical SOAP derivatives for periodic systems HOT 6
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 dscribe.