Zobrazeno 1 - 10
of 93
pro vyhledávání: '"Kovalsky, Shahar"'
In recent years, many deep learning approaches have incorporated layers that solve optimization problems (e.g., linear, quadratic, and semidefinite programs). Integrating these optimization problems as differentiable layers requires computing the der
Externí odkaz:
http://arxiv.org/abs/2410.06324
Autor:
Dan, Tingting, Ding, Jiaqi, Wei, Ziquan, Kovalsky, Shahar Z, Kim, Minjeong, Kim, Won Hwa, Wu, Guorong
Graph neural networks (GNNs) are widely used in domains like social networks and biological systems. However, the locality assumption of GNNs, which limits information exchange to neighboring nodes, hampers their ability to capture long-range depende
Externí odkaz:
http://arxiv.org/abs/2307.00222
The classical $\textit{Procrustes}$ problem is to find a rigid motion (orthogonal transformation and translation) that best aligns two given point-sets in the least-squares sense. The $\textit{Robust Procrustes}$ problem is an important variant, in w
Externí odkaz:
http://arxiv.org/abs/2207.08592
Autor:
Daubechies, Ingrid, DeVore, Ronald, Dym, Nadav, Faigenbaum-Golovin, Shira, Kovalsky, Shahar Z., Lin, Kung-Ching, Park, Josiah, Petrova, Guergana, Sober, Barak
In the desire to quantify the success of neural networks in deep learning and other applications, there is a great interest in understanding which functions are efficiently approximated by the outputs of neural networks. By now, there exists a variet
Externí odkaz:
http://arxiv.org/abs/2107.13191
Autor:
Kovalsky, Shahar Z., Aigerman, Noam, Daubechies, Ingrid, Kazhdan, Michael, Lu, Jianfeng, Steinerberger, Stefan
We formulate a novel characterization of a family of invertible maps between two-dimensional domains. Our work follows two classic results: The Rad\'o-Kneser-Choquet (RKC) theorem, which establishes the invertibility of harmonic maps into a convex pl
Externí odkaz:
http://arxiv.org/abs/2001.01322
Autor:
Dov, David, Elliott Range, Danielle, Cohen, Jonathan, Bell, Jonathan, Rocke, Daniel J., Kahmke, Russel R., Weiss-Meilik, Ahuva, Lee, Walter T., Henao, Ricardo, Carin, Lawrence, Kovalsky, Shahar Z.
Publikováno v:
In The American Journal of Pathology September 2023 193(9):1185-1194
Autor:
Dov, David, Kovalsky, Shahar Ziv, Assaad, Serge, Cohen, Avani A. Pendse Jonathan, Range, Danielle Elliott, Henao, Ricardo, Carin, Lawrence
We consider machine-learning-based thyroid-malignancy prediction from cytopathology whole-slide images (WSI). Multiple instance learning (MIL) approaches, typically used for the analysis of WSIs, divide the image (bag) into patches (instances), which
Externí odkaz:
http://arxiv.org/abs/1904.12739
Autor:
Dym, Nadav, Kovalsky, Shahar Ziv
In recent years, several branch-and-bound (BnB) algorithms have been proposed to globally optimize rigid registration problems. In this paper, we suggest a general framework to improve upon the BnB approach, which we name Quasi BnB. Quasi BnB replace
Externí odkaz:
http://arxiv.org/abs/1904.02204
Autor:
Dov, David, Kovalsky, Shahar, Cohen, Jonathan, Range, Danielle, Henao, Ricardo, Carin, Lawrence
Publikováno v:
Proceedings of Machine Learning Research, 2019, Vol. 106
We consider preoperative prediction of thyroid cancer based on ultra-high-resolution whole-slide cytopathology images. Inspired by how human experts perform diagnosis, our approach first identifies and classifies diagnostic image regions containing i
Externí odkaz:
http://arxiv.org/abs/1904.00839
Publikováno v:
Methods Ecol Evol (2019)
Point 1: Shape characterizers are metrics that quantify aspects of the overall geometry of a 3D digital surface. When computed for biological objects, the values of a shape characterizer are largely independent of homology interpretations and often c
Externí odkaz:
http://arxiv.org/abs/1901.06318