Zobrazeno 1 - 10
of 380
pro vyhledávání: '"Gregor, N"'
Autor:
Midgley, Laurence Illing, Stimper, Vincent, Simm, Gregor N. C., Schölkopf, Bernhard, Hernández-Lobato, José Miguel
Normalizing flows are tractable density models that can approximate complicated target distributions, e.g. Boltzmann distributions of physical systems. However, current methods for training flows either suffer from mode-seeking behavior, use samples
Externí odkaz:
http://arxiv.org/abs/2208.01893
Creating fast and accurate force fields is a long-standing challenge in computational chemistry and materials science. Recently, several equivariant message passing neural networks (MPNNs) have been shown to outperform models built using other approa
Externí odkaz:
http://arxiv.org/abs/2206.07697
Autor:
Batatia, Ilyes, Batzner, Simon, Kovács, Dávid Péter, Musaelian, Albert, Simm, Gregor N. C., Drautz, Ralf, Ortner, Christoph, Kozinsky, Boris, Csányi, Gábor
The rapid progress of machine learning interatomic potentials over the past couple of years produced a number of new architectures. Particularly notable among these are the Atomic Cluster Expansion (ACE), which unified many of the earlier ideas aroun
Externí odkaz:
http://arxiv.org/abs/2205.06643
Autor:
Midgley, Laurence Illing, Stimper, Vincent, Simm, Gregor N. C., Hernández-Lobato, José Miguel
Normalizing flows are flexible, parameterized distributions that can be used to approximate expectations from intractable distributions via importance sampling. However, current flow-based approaches are limited on challenging targets where they eith
Externí odkaz:
http://arxiv.org/abs/2111.11510
Autor:
García-Ortegón, Miguel, Simm, Gregor N. C., Tripp, Austin J., Hernández-Lobato, José Miguel, Bender, Andreas, Bacallado, Sergio
The field of machine learning for drug discovery is witnessing an explosion of novel methods. These methods are often benchmarked on simple physicochemical properties such as solubility or general druglikeness, which can be readily computed. However,
Externí odkaz:
http://arxiv.org/abs/2110.15486
Publikováno v:
International Conference on Learning Representations, 2021
Automating molecular design using deep reinforcement learning (RL) has the potential to greatly accelerate the search for novel materials. Despite recent progress on leveraging graph representations to design molecules, such methods are fundamentally
Externí odkaz:
http://arxiv.org/abs/2011.12747
Publikováno v:
Proceedings of the 37th International Conference on Machine Learning, Vienna, Austria, PMLR 119, 2020
Automating molecular design using deep reinforcement learning (RL) holds the promise of accelerating the discovery of new chemical compounds. Existing approaches work with molecular graphs and thus ignore the location of atoms in space, which restric
Externí odkaz:
http://arxiv.org/abs/2002.07717
Publikováno v:
Proceedings of the 37th International Conference on Machine Learning, Vienna, Austria, PMLR 119, 2020
Great computational effort is invested in generating equilibrium states for molecular systems using, for example, Markov chain Monte Carlo. We present a probabilistic model that generates statistically independent samples for molecules from their gra
Externí odkaz:
http://arxiv.org/abs/1909.11459
Publikováno v:
J. Comput. Chem. 41 (2020) 1144-1155
Solvation is a notoriously difficult and nagging problem for the rigorous theoretical description of chemistry in the liquid phase. Successes and failures of various approaches ranging from implicit solvation modeling through dielectric continuum emb
Externí odkaz:
http://arxiv.org/abs/1909.06664
For the task of concurrently detecting and categorizing objects, the medical imaging community commonly adopts methods developed on natural images. Current state-of-the-art object detectors are comprised of two stages: the first stage generates regio
Externí odkaz:
http://arxiv.org/abs/1907.12915