Zobrazeno 1 - 10
of 13
pro vyhledávání: '"Kevin Ryczko"'
Publikováno v:
Applied AI Letters, Vol 3, Iss 4, Pp n/a-n/a (2022)
Abstract We introduce twin neural network regression (TNNR). This method predicts differences between the target values of two different data points rather than the targets themselves. The solution of a traditional regression problem is then obtained
Externí odkaz:
https://doaj.org/article/efdecc5034284884800cf421ed52ea3e
Autor:
Kevin Ryczko, Kyle Mills, Edward H. Sargent, Isaac Tamblyn, Hitarth Choubisa, Mikhail Askerka, Oleksandr Voznyy
Publikováno v:
Matter. 3:433-448
Mapping materials science problems onto computational frameworks suitable for machine learning can accelerate materials discovery. Combining proposed crystal site feature embedding (CSFE) representation with convolutional and extensive deep neural ne
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::cbe5cde646b070b23a3d927981dd15cb
https://doi.org/10.1016/j.matt.2020.04.016
https://doi.org/10.1016/j.matt.2020.04.016
Publikováno v:
Journal of chemical theory and computation. 18(2)
We use voxel deep neural networks to predict energy densities and functional derivatives of electron kinetic energies for the Thomas-Fermi model and Kohn-Sham density functional theory calculations. We show that the ground-state electron density can
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1c6f6a6b1e748b79438076121bf96c3b
https://pubmed.ncbi.nlm.nih.gov/34995061
https://pubmed.ncbi.nlm.nih.gov/34995061
We present two machine learning methodologies that are capable of predicting diffusion Monte Carlo (DMC) energies with small data sets (≈60 DMC calculations in total). The first uses voxel deep neural networks (VDNNs) to predict DMC energy densitie
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a66cd154377290c4998d58954429cdd6
We introduce an inverse design framework based on artificial neural networks, genetic algorithms, and tight-binding calculations, capable to optimize the very large configuration space of nanoelectronic devices. Our non-linear optimization procedure
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::11d3f87fa8a11f24cf3632b943b4de83
http://arxiv.org/abs/2007.07070
http://arxiv.org/abs/2007.07070
Publikováno v:
Computational Materials Science. 149:134-142
We introduce a new method, called CNNAS (convolutional neural networks for atomistic systems), for calculating the total energy of atomic systems which rivals the computational cost of empirical potentials while maintaining the accuracy of \emph{ab i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ca22b86ae596edbda4fc9a411f599522
https://doi.org/10.1016/j.commatsci.2018.03.005
https://doi.org/10.1016/j.commatsci.2018.03.005
Publikováno v:
ECS Meeting Abstracts. :604-604
Raman spectrum is a common spectroscopic tool used in materials synthesis and characterization. The width and shift of Raman peaks are commonly used in characterization of graphene samples. In this presentation, I will highlight our efforts in using
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5d3defcf430da21201d05a396ca11da2
https://doi.org/10.1149/ma2021-0112604mtgabs
https://doi.org/10.1149/ma2021-0112604mtgabs
Publikováno v:
Physical Review A, vol 100, iss 2
PHYSICAL REVIEW A, vol 100, iss 2
PHYSICAL REVIEW A, vol 100, iss 2
We show that deep neural networks can be integrated into, or fully replace, the Kohn-Sham density functional theory (DFT) scheme for multielectron systems in simple harmonic oscillator and random external potentials with no feature engineering. We fi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6911716ed42f9e03a7f2ee5499a6c74d
Publikováno v:
Chemical Science
We present a physically-motivated topology of a deep neural network that can efficiently infer extensive parameters (such as energy, entropy, or number of particles) of arbitrarily large systems, doing so with O(N) scaling. We use a form of domain de
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c5c56e272dc24c22fc451164ea519efd
http://arxiv.org/abs/1708.06686
http://arxiv.org/abs/1708.06686
Hashkat (http://hashkat.org) is a free, open source, agent based simulation software package designed to simulate large-scale online social networks (e.g. Twitter, Facebook, LinkedIn, etc). It allows for dynamic agent generation, edge creation, and i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b8cfd353d3b71a9d86cb32620feb4326
https://nrc-publications.canada.ca/eng/view/object/?id=82369085-b48d-4d51-a2f7-6bb31f35b35e
https://nrc-publications.canada.ca/eng/view/object/?id=82369085-b48d-4d51-a2f7-6bb31f35b35e