Generalized neural-network representation of high-dimensional potential-energy surfaces.

By J. Behler, Michele Parrinello. 2007

3,462 citations recorded by the source corpus.

Subfields: Atomic and Molecular Physics, and Optics, Materials Chemistry, Physical and Theoretical Chemistry, AI for Physical Sciences

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Atomic and Molecular Physics, and Optics

1. Alexander V. Shapeev
2. Yuri Mishin
3. Evgeny V. Podryabinkin
4. Risi Kondor
5. K. Müller
6. Gábor Csányi
7. J. Behler
8. Alexandre Tkatchenko

In Materials Chemistry

1. Tess E. Smidt
2. Yuri Mishin
3. Risi Kondor
4. Alexander V. Shapeev
5. K. Müller
6. Michael Gastegger
7. Frank No'e
8. Kristof T. Schütt

In Physical and Theoretical Chemistry

1. Risi Kondor
2. Jian Tang
3. Sam Schoenholz
4. Tess E. Smidt
5. Kristof T. Schütt
6. Stephan Günnemann
7. Evgeny V. Podryabinkin
8. Alexander V. Shapeev

In AI for Physical Sciences

1. K. Müller
2. Risi Kondor
3. Tess E. Smidt
4. Alexander V. Shapeev
5. Sam Schoenholz
6. Frank No'e
7. Michael Gastegger
8. Stephan Günnemann

Citations in the corpus

• Neural Message Passing for Quantum Chemistry (2017, methodology): “The work of Behler & Parrinello (2007) used a representation that was manifestly invariant to graph isomorphism, but has difficulty when applied to systems with more than three species of atoms and fails to generalize to novel compositions.”
• Directional Message Passing for Molecular Graphs (2020, methodology): “…way of using machine learning for predicting molecular properties is combining an expressive, hand-crafted representation of the atomic neighborhood (Bartók et al., 2013) with Gaussian processes (Bartók et al., 2010; 2017; Chmiela et al., 2017) or neural networks (Behler & Parrinello, 2007).”
• Cormorant: Covariant Molecular Neural Networks (2019, background): “…years a burgeoning community has formed around trying to use machine learning to learn more descriptive force fields directly from DFT computations [Behler and Parrinello, 2007, Bartók et al., 2010, Rupp et al., 2012, Shapeev, 2015, Chmiela et al., 2016, Zhang et al., 2018, Schütt et al., 2017,…”
• N-body Networks: a Covariant Hierarchical Neural Network Architecture for Learning Atomic Potentials (2018, background): “…over ten years ago, machine learning entered this field, promising to bridge the gap between the quantum and classical worlds by learning the aggregate force on each atom as a function of the positons of its neighbors from a relatively small number of DFT calculations (Behler & Parrinello, 2007).”
• Wavelet Scattering Regression of Quantum Chemical Energies (2016, background): “Such algorithms for potential energy surface fitting of one molecule or material have been developed for more than two decades, tracing back to [45] with further contributions in [32, 8, 7, 42, 5, 49].”