Zobrazeno 1 - 10
of 123
pro vyhledávání: '"Bernal, Edgar A."'
Autor:
Sartipi, Shadi, Bernal, Edgar A.
One of the prevailing trends in the machine- and deep-learning community is to gravitate towards the use of increasingly larger models in order to keep pushing the state-of-the-art performance envelope. This tendency makes access to the associated te
Externí odkaz:
http://arxiv.org/abs/2305.17119
Autor:
Bernal, Edgar A.
Deep generative frameworks including GANs and normalizing flow models have proven successful at filling in missing values in partially observed data samples by effectively learning -- either explicitly or implicitly -- complex, high-dimensional stati
Externí odkaz:
http://arxiv.org/abs/2104.01482
Autor:
Bernal, Edgar A., Hauenstein, Jonathan D., Mehta, Dhagash, Regan, Margaret H., Tang, Tingting
Parameterized systems of polynomial equations arise in many applications in science and engineering with the real solutions describing, for example, equilibria of a dynamical system, linkages satisfying design constraints, and scene reconstruction in
Externí odkaz:
http://arxiv.org/abs/2006.14078
Publikováno v:
2020 Computer Vision and Pattern Recognition (CVPR)
We consider the topic of data imputation, a foundational task in machine learning that addresses issues with missing data. To that end, we propose MCFlow, a deep framework for imputation that leverages normalizing flow generative models and Monte Car
Externí odkaz:
http://arxiv.org/abs/2003.12628
Myotonia, which refers to delayed muscle relaxation after contraction, is the main symptom of myotonic dystrophy patients. We propose a hierarchical attention-based temporal convolutional network (HA-TCN) for myotonic dystrohpy diagnosis from handgri
Externí odkaz:
http://arxiv.org/abs/1903.11748
Autor:
Bernal, Edgar A., Hauenstein, Jonathan D., Mehta, Dhagash, Regan, Margaret H., Tang, Tingting
Publikováno v:
In Journal of Symbolic Computation March-April 2023 115:409-426
We investigate the topics of sensitivity and robustness in feedforward and convolutional neural networks. Combining energy landscape techniques developed in computational chemistry with tools drawn from formal methods, we produce empirical evidence i
Externí odkaz:
http://arxiv.org/abs/1810.11726
Publikováno v:
Phys. Rev. E 97, 052307 (2018)
Training an artificial neural network involves an optimization process over the landscape defined by the cost (loss) as a function of the network parameters. We explore these landscapes using optimisation tools developed for potential energy landscap
Externí odkaz:
http://arxiv.org/abs/1804.02411
Autor:
Yang, Xitong, Ramesh, Palghat, Chitta, Radha, Madhvanath, Sriganesh, Bernal, Edgar A., Luo, Jiebo
In recent years, Deep Learning has been successfully applied to multimodal learning problems, with the aim of learning useful joint representations in data fusion applications. When the available modalities consist of time series data such as video,
Externí odkaz:
http://arxiv.org/abs/1704.03152
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.