Zobrazeno 1 - 10
of 19
pro vyhledávání: '"Bińkowski, Mikołaj"'
Autor:
Alayrac, Jean-Baptiste, Donahue, Jeff, Luc, Pauline, Miech, Antoine, Barr, Iain, Hasson, Yana, Lenc, Karel, Mensch, Arthur, Millican, Katie, Reynolds, Malcolm, Ring, Roman, Rutherford, Eliza, Cabi, Serkan, Han, Tengda, Gong, Zhitao, Samangooei, Sina, Monteiro, Marianne, Menick, Jacob, Borgeaud, Sebastian, Brock, Andrew, Nematzadeh, Aida, Sharifzadeh, Sahand, Binkowski, Mikolaj, Barreira, Ricardo, Vinyals, Oriol, Zisserman, Andrew, Simonyan, Karen
Building models that can be rapidly adapted to novel tasks using only a handful of annotated examples is an open challenge for multimodal machine learning research. We introduce Flamingo, a family of Visual Language Models (VLM) with this ability. We
Externí odkaz:
http://arxiv.org/abs/2204.14198
In this paper we propose a new generative model of text, Step-unrolled Denoising Autoencoder (SUNDAE), that does not rely on autoregressive models. Similarly to denoising diffusion techniques, SUNDAE is repeatedly applied on a sequence of tokens, sta
Externí odkaz:
http://arxiv.org/abs/2112.06749
Autor:
Koppula, Skanda, Bapst, Victor, Huertas-Company, Marc, Blackwell, Sam, Grabska-Barwinska, Agnieszka, Dieleman, Sander, Huber, Andrea, Antropova, Natasha, Binkowski, Mikolaj, Openshaw, Hannah, Recasens, Adria, Caro, Fernando, Deke, Avishai, Dubois, Yohan, Ferrero, Jesus Vega, Koo, David C., Primack, Joel R., Back, Trevor
Fine-grained estimation of galaxy merger stages from observations is a key problem useful for validation of our current theoretical understanding of galaxy formation. To this end, we demonstrate a CNN-based regression model that is able to predict, f
Externí odkaz:
http://arxiv.org/abs/2102.05182
Modern text-to-speech synthesis pipelines typically involve multiple processing stages, each of which is designed or learnt independently from the rest. In this work, we take on the challenging task of learning to synthesise speech from normalised te
Externí odkaz:
http://arxiv.org/abs/2006.03575
Autor:
Bińkowski, Mikołaj, Donahue, Jeff, Dieleman, Sander, Clark, Aidan, Elsen, Erich, Casagrande, Norman, Cobo, Luis C., Simonyan, Karen
Generative adversarial networks have seen rapid development in recent years and have led to remarkable improvements in generative modelling of images. However, their application in the audio domain has received limited attention, and autoregressive m
Externí odkaz:
http://arxiv.org/abs/1909.11646
Unsupervised domain transfer is the task of transferring or translating samples from a source distribution to a different target distribution. Current solutions unsupervised domain transfer often operate on data on which the modes of the distribution
Externí odkaz:
http://arxiv.org/abs/1905.12760
In this paper we investigate the endogenous information contained in four liquidity variables at a five minutes time scale on equity markets around the world: the traded volume, the bid-ask spread, the volatility and the volume at first limits of the
Externí odkaz:
http://arxiv.org/abs/1811.03766
Publikováno v:
Advances in Neural Information Processing Systems 31 (NeurIPS 2018), 6700-6710
We propose a principled method for gradient-based regularization of the critic of GAN-like models trained by adversarially optimizing the kernel of a Maximum Mean Discrepancy (MMD). We show that controlling the gradient of the critic is vital to havi
Externí odkaz:
http://arxiv.org/abs/1805.11565
We investigate the training and performance of generative adversarial networks using the Maximum Mean Discrepancy (MMD) as critic, termed MMD GANs. As our main theoretical contribution, we clarify the situation with bias in GAN loss functions raised
Externí odkaz:
http://arxiv.org/abs/1801.01401
We propose Significance-Offset Convolutional Neural Network, a deep convolutional network architecture for regression of multivariate asynchronous time series. The model is inspired by standard autoregressive (AR) models and gating mechanisms used in
Externí odkaz:
http://arxiv.org/abs/1703.04122