Zobrazeno 1 - 10
of 35
pro vyhledávání: '"Kurach, Karol"'
Autor:
Kurach, Karol, Raichuk, Anton, Stańczyk, Piotr, Zając, Michał, Bachem, Olivier, Espeholt, Lasse, Riquelme, Carlos, Vincent, Damien, Michalski, Marcin, Bousquet, Olivier, Gelly, Sylvain
Recent progress in the field of reinforcement learning has been accelerated by virtual learning environments such as video games, where novel algorithms and ideas can be quickly tested in a safe and reproducible manner. We introduce the Google Resear
Externí odkaz:
http://arxiv.org/abs/1907.11180
Autor:
Unterthiner, Thomas, van Steenkiste, Sjoerd, Kurach, Karol, Marinier, Raphael, Michalski, Marcin, Gelly, Sylvain
Recent advances in deep generative models have lead to remarkable progress in synthesizing high quality images. Following their successful application in image processing and representation learning, an important next step is to consider videos. Lear
Externí odkaz:
http://arxiv.org/abs/1812.01717
Autor:
Zamorski, Maciej, Zięba, Maciej, Klukowski, Piotr, Nowak, Rafał, Kurach, Karol, Stokowiec, Wojciech, Trzciński, Tomasz
Deep generative architectures provide a way to model not only images but also complex, 3-dimensional objects, such as point clouds. In this work, we present a novel method to obtain meaningful representations of 3D shapes that can be used for challen
Externí odkaz:
http://arxiv.org/abs/1811.07605
Deep generative models seek to recover the process with which the observed data was generated. They may be used to synthesize new samples or to subsequently extract representations. Successful approaches in the domain of images are driven by several
Externí odkaz:
http://arxiv.org/abs/1810.10340
Generative adversarial networks (GANs) are a class of deep generative models which aim to learn a target distribution in an unsupervised fashion. While they were successfully applied to many problems, training a GAN is a notoriously challenging task
Externí odkaz:
http://arxiv.org/abs/1807.04720
We propose a new learning paradigm called Deep Memory. It has the potential to completely revolutionize the Machine Learning field. Surprisingly, this paradigm has not been reinvented yet, unlike Deep Learning. At the core of this approach is the \te
Externí odkaz:
http://arxiv.org/abs/1803.11203
Generative adversarial networks (GAN) are a powerful subclass of generative models. Despite a very rich research activity leading to numerous interesting GAN algorithms, it is still very hard to assess which algorithm(s) perform better than others. W
Externí odkaz:
http://arxiv.org/abs/1711.10337
The selection of hyper-parameters is critical in Deep Learning. Because of the long training time of complex models and the availability of compute resources in the cloud, "one-shot" optimization schemes - where the sets of hyper-parameters are selec
Externí odkaz:
http://arxiv.org/abs/1706.03200
Autor:
Bousquet, Olivier, Gelly, Sylvain, Kurach, Karol, Schoenauer, Marc, Sebag, Michele, Teytaud, Olivier, Vincent, Damien
This paper aims at one-shot learning of deep neural nets, where a highly parallel setting is considered to address the algorithm calibration problem - selecting the best neural architecture and learning hyper-parameter values depending on the dataset
Externí odkaz:
http://arxiv.org/abs/1706.03199
Autor:
Kurach, Karol, Gelly, Sylvain, Jastrzebski, Michal, Haeusser, Philip, Teytaud, Olivier, Vincent, Damien, Bousquet, Olivier
Generic text embeddings are successfully used in a variety of tasks. However, they are often learnt by capturing the co-occurrence structure from pure text corpora, resulting in limitations of their ability to generalize. In this paper, we explore mo
Externí odkaz:
http://arxiv.org/abs/1705.08386