Zobrazeno 1 - 10
of 450
pro vyhledávání: '"Pereira, Marcus"'
Publikováno v:
Robotics: Science and Systems (RSS), 2022
In this work, we propose a novel safe and scalable decentralized solution for multi-agent control in the presence of stochastic disturbances. Safety is mathematically encoded using stochastic control barrier functions and safe controls are computed b
Externí odkaz:
http://arxiv.org/abs/2202.10658
Publikováno v:
In Kidney International Reports August 2024 9(8):2337-2352
In this paper, we introduce a novel deep learning based solution to the Powered-Descent Guidance (PDG) problem, grounded in principles of nonlinear Stochastic Optimal Control (SOC) and Feynman-Kac theory. Our algorithm solves the PDG problem by frami
Externí odkaz:
http://arxiv.org/abs/2109.00183
Publikováno v:
Conference on Robot Learning 2020
This paper introduces a new formulation for stochastic optimal control and stochastic dynamic optimization that ensures safety with respect to state and control constraints. The proposed methodology brings together concepts such as Forward-Backward S
Externí odkaz:
http://arxiv.org/abs/2009.01196
In this work we propose the use of adaptive stochastic search as a building block for general, non-convex optimization operations within deep neural network architectures. Specifically, for an objective function located at some layer in the network a
Externí odkaz:
http://arxiv.org/abs/2006.11992
Autor:
Blumberg, Emily A., Nam, Hannah H., Covington, Shandie, Danziger-Isakov, Lara, Kumar, Deepali, Michaels, Marian G., Razonable, Raymund R., Pereira, Marcus R.
Publikováno v:
In American Journal of Transplantation October 2023 23(10):1507-1510
Autor:
Agrawal, Neerja, Pereira, Marcus, Ranganna, Karthik, Wolfe, Cameron, Friedman-Moraco, Rachel, Kitchens, William, Adebiyi, Oluwafisayo, Kubal, Chandrashekhar, Cameron, Andrew, Desai, Niraj, Durand, Christine, Ottmann, Shane, Elias, Nahel, Gilbert, Alexander, Smith, Coleman, Castillo-Lugo, Jose A., Florman, Sander, Segev, Dorry L., Massie, Allan, Mehta, Sapna, Stosor, Valentina, Hand, Jonathan, Blumberg, Emily, Santos, Carlos A.Q., Goldberg, Ryan, Mehta, Shikha, Cannon, Robert, Giorgakis, Emmanouil, Schaenman, Joanna, Aslam, Saima, Stock, Peter, Price, Jennifer, Apewokin, Senu, Benamu, Esther, Spaggiari, Mario, Baddley, John, Morris, Michele I., Simkins, Jacques, Pruett, Timothy, Haidar, Ghady, Wojciechowski, David, Agarwal, Avinash, Balaraman, Vasanthi, Gupta, Gaurav, Chapman, Will, Muthukumar, Thangamani, Small, Catherine B., Malinis, Maricar, Durand, Christine M., Martinez, Nina, Neumann, Karl, Benedict, Reed C., Baker, Arthur W., Wolfe, Cameron R., Shetty, Aneesha, Dietch, Zachary C., Goudy, Leah, Callegari, Michelle A., Massie, Allan B., Brown, Diane, Cochran, Willa, Muzaale, Abimereki, Fine, Derek, Tobian, Aaron A.R., Winkler, Cheryl A., Al Ammary, Fawaz
Publikováno v:
In The Lancet Regional Health - Americas August 2023 24
Publikováno v:
Proceedings of Machine Learning Research, Volume 100, Pages 1231-1246, 2019
Systems involving Partial Differential Equations (PDEs) have recently become more popular among the machine learning community. However prior methods usually treat infinite dimensional problems in finite dimensions with Reduced Order Models. This lea
Externí odkaz:
http://arxiv.org/abs/1907.04006
This paper presents a novel approach to numerically solve stochastic differential games for nonlinear systems. The proposed approach relies on the nonlinear Feynman-Kac theorem that establishes a connection between parabolic deterministic partial dif
Externí odkaz:
http://arxiv.org/abs/1906.04771
We present a deep recurrent neural network architecture to solve a class of stochastic optimal control problems described by fully nonlinear Hamilton Jacobi Bellmanpartial differential equations. Such PDEs arise when one considers stochastic dynamics
Externí odkaz:
http://arxiv.org/abs/1906.04762