👋 Powered by Foam
This repository stores the references relevant to [Toward-the-Exact-Exchange–Correlation-Potential]
A nice citation graph for [Toward-the-Exact-Exchange–Correlation-Potential] can be found here
Another graph derived from Foam 
To interact with Foam, follow the instruction from foam-template
Although it is perfectly fine to directly modify .md files using whatever markdown editors you are familiar with, using foam will enable more powerful features such as wiki-links and note graphs.
- Journals like [2021-03-04] is used for house-keeping.
- Action items can be found at [todo] (maintenance stuff, non-academic).
- [inbox] stores unfiltered unorganized raw information/references, which will later on be organized and put into corresponding references.
- Really good comprehensive Meta-learning lectures by Chelsea Finn.
- Quick bits on Meta-learning: slides
- ICML 2019 Meta-learning Tutorial with videos, slides
- a blog post on the equivariance of Alphafold 2 with some nice illustrations
- iterative 3D equivariance (SE(3) transformer)
| Name | Authors | Dataset | Model | Translation invariance | URL | Code | Library | Year | Status | Journals | Is-Survey |
|---|---|---|---|---|---|---|---|---|---|---|---|
| [Machine-learning-accurate-exchange-and-correlation] Machine learning accurate exchange and correlation functionals of the electronic density |
MOB-ML24 and MB-Pol9–11, sGDML23 | BPNN | Symmetrizer | paper | neuralxc | Pytorch, TF | 2020 | No | |||
| [Learning-the-exchange-correlation-functional] Learning the exchange-correlation functional from nature with fully differentiable density functional theory |
NIST CCCBDB | paper | xitorch | Pytorch | 2021 | No | |||||
| [Accurate-transferable-multitask-prediction] Accurate and transferable multitask prediction of chemical properties with an atoms-in-molecules neural network |
ANI-1x, Comp6 | MLP | Embedding? | paper | aimnet | Pytorch | 2019 | No | |||
| [Less-is-more] Less is more: sampling chemical space with active learning |
ANI-1, ANI-1x, Comp6 | Active learning | arxiv | ani-tools comp6 | No | ||||||
| [Completing-dft-by-ml] Completing density functional theory by machine learning hidden messages from molecules |
Nagai et al | MLP | nature | nnfunctional | Pytorch | 2020/2019 | No | ||||
| [Neural-network-Kohn-Sham-exchange-correlation-potetial] Neural-network Kohn-Sham exchange-correlation potential and its out-of-training transferability |
Nagai et al | arxiv | 2018 | No | |||||||
| [Toward-the-Exact-Exchange–Correlation-Potential] Toward the Exact Exchange–Correlation Potential: A Three-Dimensional Convolutional Neural Network Construct |
3D CNN | regularization term (loss) | jpcl | N/A | 2019 | No | |||||
| [Kohn-Sham-Equations-as-Regularizer] Kohn-Sham Equations as Regularizer: Building Prior Knowledge into Machine-Learned Physics |
Li Li et al | Global Convolution | paper supp | jax-dft | Jax | 2020 | No | ||||
| [Learning-to-Approximate-Density-functionals] Learning to Approximate Density Functionals |
Li Li et al | paper | 2021 | No | |||||||
| [ML-for-the-solution-of-the-Schrödin] Machine learning for the solution of the Schrödinger equation |
paper | N/A | 2021 | Yes |