Zobrazeno 1 - 10
of 77
pro vyhledávání: '"Gaunt, Alexander L."'
Autor:
Yang, Sherry, Batzner, Simon, Gao, Ruiqi, Aykol, Muratahan, Gaunt, Alexander L., McMorrow, Brendan, Rezende, Danilo J., Schuurmans, Dale, Mordatch, Igor, Cubuk, Ekin D.
Generative models trained at scale can now produce text, video, and more recently, scientific data such as crystal structures. In applications of generative approaches to materials science, and in particular to crystal structures, the guidance from t
Externí odkaz:
http://arxiv.org/abs/2409.06762
Autor:
Schaarschmidt, Michael, Riviere, Morgane, Ganose, Alex M., Spencer, James S., Gaunt, Alexander L., Kirkpatrick, James, Axelrod, Simon, Battaglia, Peter W., Godwin, Jonathan
We present evidence that learned density functional theory (``DFT'') force fields are ready for ground state catalyst discovery. Our key finding is that relaxation using forces from a learned potential yields structures with similar or lower energy t
Externí odkaz:
http://arxiv.org/abs/2209.12466
Autor:
Xie, Tian, Bapst, Victor, Gaunt, Alexander L., Obika, Annette, Back, Trevor, Hassabis, Demis, Kohli, Pushmeet, Kirkpatrick, James
Machine Learning (ML) has the potential to accelerate discovery of new materials and shed light on useful properties of existing materials. A key difficulty when applying ML in Materials Science is that experimental datasets of material properties te
Externí odkaz:
http://arxiv.org/abs/2103.13795
Autor:
Yin, Pengcheng, Neubig, Graham, Allamanis, Miltiadis, Brockschmidt, Marc, Gaunt, Alexander L.
We introduce the problem of learning distributed representations of edits. By combining a "neural editor" with an "edit encoder", our models learn to represent the salient information of an edit and can be used to apply edits to new inputs. We experi
Externí odkaz:
http://arxiv.org/abs/1810.13337
Autor:
Wu, Anqi, Nowozin, Sebastian, Meeds, Edward, Turner, Richard E., Hernández-Lobato, José Miguel, Gaunt, Alexander L.
Bayesian neural networks (BNNs) hold great promise as a flexible and principled solution to deal with uncertainty when learning from finite data. Among approaches to realize probabilistic inference in deep neural networks, variational Bayes (VB) is t
Externí odkaz:
http://arxiv.org/abs/1810.03958
Autor:
Navon, Nir, Eigen, Christoph, Zhang, Jinyi, Lopes, Raphael, Gaunt, Alexander L., Fujimoto, Kazuya, Tsubota, Makoto, Smith, Robert P., Hadzibabic, Zoran
Publikováno v:
Science 366, 382 (2019)
Scale-invariant fluxes are the defining property of turbulent cascades, but their direct measurement is a notorious problem. Here we perform such a measurement for a direct energy cascade in a turbulent quantum gas. Using a time-periodic force, we in
Externí odkaz:
http://arxiv.org/abs/1807.07564
Graphs are ubiquitous data structures for representing interactions between entities. With an emphasis on the use of graphs to represent chemical molecules, we explore the task of learning to generate graphs that conform to a distribution observed in
Externí odkaz:
http://arxiv.org/abs/1805.09076
Generative models for source code are an interesting structured prediction problem, requiring to reason about both hard syntactic and semantic constraints as well as about natural, likely programs. We present a novel model for this problem that uses
Externí odkaz:
http://arxiv.org/abs/1805.08490
Autor:
Liao, Renjie, Brockschmidt, Marc, Tarlow, Daniel, Gaunt, Alexander L., Urtasun, Raquel, Zemel, Richard
We present graph partition neural networks (GPNN), an extension of graph neural networks (GNNs) able to handle extremely large graphs. GPNNs alternate between locally propagating information between nodes in small subgraphs and globally propagating i
Externí odkaz:
http://arxiv.org/abs/1803.06272
Autor:
Gaunt, Alexander L., Johnson, Matthew A., Riechert, Maik, Tarlow, Daniel, Tomioka, Ryota, Vytiniotis, Dimitrios, Webster, Sam
New types of machine learning hardware in development and entering the market hold the promise of revolutionizing deep learning in a manner as profound as GPUs. However, existing software frameworks and training algorithms for deep learning have yet
Externí odkaz:
http://arxiv.org/abs/1705.09786