Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Macdonald, Kincaid"'
Autor:
MacDonald, Kincaid, Bhaskar, Dhananjay, Thampakkul, Guy, Nguyen, Nhi, Zhang, Joia, Perlmutter, Michael, Adelstein, Ian, Krishnaswamy, Smita
We consider the problem of embedding point cloud data sampled from an underlying manifold with an associated flow or velocity. Such data arises in many contexts where static snapshots of dynamic entities are measured, including in high-throughput bio
Externí odkaz:
http://arxiv.org/abs/2308.00176
Autor:
Tong, Alexander, Wenkel, Frederik, Bhaskar, Dhananjay, Macdonald, Kincaid, Grady, Jackson, Perlmutter, Michael, Krishnaswamy, Smita, Wolf, Guy
We propose a new graph neural network (GNN) module, based on relaxations of recently proposed geometric scattering transforms, which consist of a cascade of graph wavelet filters. Our learnable geometric scattering (LEGS) module enables adaptive tuni
Externí odkaz:
http://arxiv.org/abs/2208.07458
Autor:
Bhaskar, Dhananjay, MacDonald, Kincaid, Fasina, Oluwadamilola, Thomas, Dawson, Rieck, Bastian, Adelstein, Ian, Krishnaswamy, Smita
Publikováno v:
Thirty-sixth Conference on Neural Information Processing Systems (NeurIPS 2022)
We introduce a new intrinsic measure of local curvature on point-cloud data called diffusion curvature. Our measure uses the framework of diffusion maps, including the data diffusion operator, to structure point cloud data and define local curvature
Externí odkaz:
http://arxiv.org/abs/2206.03977
Autor:
Tong, Alexander, Huguet, Guillaume, Natik, Amine, MacDonald, Kincaid, Kuchroo, Manik, Coifman, Ronald, Wolf, Guy, Krishnaswamy, Smita
We propose a new fast method of measuring distances between large numbers of related high dimensional datasets called the Diffusion Earth Mover's Distance (EMD). We model the datasets as distributions supported on common data graph that is derived fr
Externí odkaz:
http://arxiv.org/abs/2102.12833
We propose a new graph neural network (GNN) module, based on relaxations of recently proposed geometric scattering transforms, which consist of a cascade of graph wavelet filters. Our learnable geometric scattering (LEGS) module enables adaptive tuni
Externí odkaz:
http://arxiv.org/abs/2010.02415
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Tong A; Yale University, Dept. of Comp. Sci., New Haven, CT, USA., Wenkel F; Université de Montréal, Dept. of Math. & Stat.; Mila - Quebec AI Institute, Montreal, QC, Canada., Macdonald K; Dept. of Math., New Haven, CT, USA., Krishnaswamy S; Dept. of Genetics, New Haven, CT, USA.; Yale University, Dept. of Comp. Sci., New Haven, CT, USA., Wolf G; Université de Montréal, Dept. of Math. & Stat.; Mila - Quebec AI Institute, Montreal, QC, Canada.
Publikováno v:
IEEE International Workshop on Machine Learning for Signal Processing : [proceedings]. IEEE International Workshop on Machine Learning for Signal Processing [IEEE Int Workshop Mach Learn Signal Process] 2021 Oct; Vol. 2021. Date of Electronic Publication: 2021 Nov 15.
Publikováno v:
ArXiv [ArXiv] 2021 Feb 25. Date of Electronic Publication: 2021 Feb 25.