Regularised body-ordered Permutation-Invariant Polynomials (aPIP) for Materials

Add to your list(s) Download to your calendar using vCal

• Cas van der Oord
• Monday 02 March 2020, 17:00-17:30
• Mott Seminar (531) room, top floor of the Mott Building, in the Cavendish Laboratory, West Cambridge..

If you have a question about this talk, please contact Bingqing Cheng .

We demonstrate the use of invariant polynomials in achieving near DFT accuracy for Si and W databases. These “aPIP” models are fitted to the explicit body-ordered decomposition of the PES and respect its translational, rotational and permutational symmetries. The low dimensionality of these models combined with careful regularisation techniques is shown to have better transferability compared to high dimensional fits.

A detailed discussion and demonstration of these different types of regularisation techniques (Tikhonov, Ridge and Laplacian) will be covered in a simple 1D case before presenting the aPIP (atomic Permutation-Invariant Polynomial) models.

This talk is part of the Machine learning in Physics, Chemistry and Materials discussion group (MLDG) series.

This talk is included in these lists:

• Hanchen DaDaDash
• Lennard-Jones Centre external
• Machine learning in Physics, Chemistry and Materials discussion group (MLDG)
• Mott Seminar (531) room, top floor of the Mott Building, in the Cavendish Laboratory, West Cambridge.

Note that ex-directory lists are not shown.