Zobrazeno 1 - 10
of 109
pro vyhledávání: '"Rosenbaum, Dan"'
Autor:
Shapira, Chen, Rosenbaum, Dan
Models that adapt their predictions based on some given contexts, also known as in-context learning, have become ubiquitous in recent years. We propose to study the behavior of such models when data is contaminated by noise. Towards this goal we use
Externí odkaz:
http://arxiv.org/abs/2411.01670
Underwater image restoration is a challenging task because of water effects that increase dramatically with distance. This is worsened by lack of ground truth data of clean scenes without water. Diffusion priors have emerged as strong image restorati
Externí odkaz:
http://arxiv.org/abs/2403.14837
Autor:
Levy, Deborah, Peleg, Amit, Pearl, Naama, Rosenbaum, Dan, Akkaynak, Derya, Korman, Simon, Treibitz, Tali
Research on neural radiance fields (NeRFs) for novel view generation is exploding with new models and extensions. However, a question that remains unanswered is what happens in underwater or foggy scenes where the medium strongly influences the appea
Externí odkaz:
http://arxiv.org/abs/2304.07743
Autor:
Bauer, Matthias, Dupont, Emilien, Brock, Andy, Rosenbaum, Dan, Schwarz, Jonathan Richard, Kim, Hyunjik
Neural fields, also known as implicit neural representations, have emerged as a powerful means to represent complex signals of various modalities. Based on this Dupont et al. (2022) introduce a framework that views neural fields as data, termed *func
Externí odkaz:
http://arxiv.org/abs/2302.03130
It is common practice in deep learning to represent a measurement of the world on a discrete grid, e.g. a 2D grid of pixels. However, the underlying signal represented by these measurements is often continuous, e.g. the scene depicted in an image. A
Externí odkaz:
http://arxiv.org/abs/2201.12204
Autor:
Rosenbaum, Dan, Garnelo, Marta, Zielinski, Michal, Beattie, Charlie, Clancy, Ellen, Huber, Andrea, Kohli, Pushmeet, Senior, Andrew W., Jumper, John, Doersch, Carl, Eslami, S. M. Ali, Ronneberger, Olaf, Adler, Jonas
Cryo-electron microscopy (cryo-EM) has revolutionized experimental protein structure determination. Despite advances in high resolution reconstruction, a majority of cryo-EM experiments provide either a single state of the studied macromolecule, or a
Externí odkaz:
http://arxiv.org/abs/2106.14108
Autor:
Mellor, John F. J., Park, Eunbyung, Ganin, Yaroslav, Babuschkin, Igor, Kulkarni, Tejas, Rosenbaum, Dan, Ballard, Andy, Weber, Theophane, Vinyals, Oriol, Eslami, S. M. Ali
We investigate using reinforcement learning agents as generative models of images (extending arXiv:1804.01118). A generative agent controls a simulated painting environment, and is trained with rewards provided by a discriminator network simultaneous
Externí odkaz:
http://arxiv.org/abs/1910.01007
Autor:
Kim, Hyunjik, Mnih, Andriy, Schwarz, Jonathan, Garnelo, Marta, Eslami, Ali, Rosenbaum, Dan, Vinyals, Oriol, Teh, Yee Whye
Neural Processes (NPs) (Garnelo et al 2018a;b) approach regression by learning to map a context set of observed input-output pairs to a distribution over regression functions. Each function models the distribution of the output given an input, condit
Externí odkaz:
http://arxiv.org/abs/1901.05761
Autor:
Garnelo, Marta, Schwarz, Jonathan, Rosenbaum, Dan, Viola, Fabio, Rezende, Danilo J., Eslami, S. M. Ali, Teh, Yee Whye
A neural network (NN) is a parameterised function that can be tuned via gradient descent to approximate a labelled collection of data with high precision. A Gaussian process (GP), on the other hand, is a probabilistic model that defines a distributio
Externí odkaz:
http://arxiv.org/abs/1807.01622
Autor:
Garnelo, Marta, Rosenbaum, Dan, Maddison, Chris J., Ramalho, Tiago, Saxton, David, Shanahan, Murray, Teh, Yee Whye, Rezende, Danilo J., Eslami, S. M. Ali
Deep neural networks excel at function approximation, yet they are typically trained from scratch for each new function. On the other hand, Bayesian methods, such as Gaussian Processes (GPs), exploit prior knowledge to quickly infer the shape of a ne
Externí odkaz:
http://arxiv.org/abs/1807.01613