Zobrazeno 1 - 10
of 360
pro vyhledávání: '"Frey, Brendan"'
In the face of rapidly accumulating genomic data, our understanding of the RNA regulatory code remains incomplete. Recent self-supervised methods in other domains have demonstrated the ability to learn rules underlying the data-generating process suc
Externí odkaz:
http://arxiv.org/abs/2310.08738
We propose generative neural network methods to generate DNA sequences and tune them to have desired properties. We present three approaches: creating synthetic DNA sequences using a generative adversarial network; a DNA-based variant of the activati
Externí odkaz:
http://arxiv.org/abs/1712.06148
Autor:
Makhzani, Alireza, Frey, Brendan
In this paper, we describe the "PixelGAN autoencoder", a generative autoencoder in which the generative path is a convolutional autoregressive neural network on pixels (PixelCNN) that is conditioned on a latent code, and the recognition path uses a g
Externí odkaz:
http://arxiv.org/abs/1706.00531
Publikováno v:
Bioinformatics (2016) 32 (12): i52-i59
Convolutional neural networks (CNN) have achieved state of the art performance on both classification and segmentation tasks. Applying CNNs to microscopy images is challenging due to the lack of datasets labeled at the single cell level. We extend th
Externí odkaz:
http://arxiv.org/abs/1511.05286
In this paper, we propose the "adversarial autoencoder" (AAE), which is a probabilistic autoencoder that uses the recently proposed generative adversarial networks (GAN) to perform variational inference by matching the aggregated posterior of the hid
Externí odkaz:
http://arxiv.org/abs/1511.05644
Despite their success, convolutional neural networks are computationally expensive because they must examine all image locations. Stochastic attention-based models have been shown to improve computational efficiency at test time, but they remain diff
Externí odkaz:
http://arxiv.org/abs/1509.06812
Autor:
Makhzani, Alireza, Frey, Brendan
In this paper, we propose a winner-take-all method for learning hierarchical sparse representations in an unsupervised fashion. We first introduce fully-connected winner-take-all autoencoders which use mini-batch statistics to directly enforce a life
Externí odkaz:
http://arxiv.org/abs/1409.2752
A new approach to maximum likelihood learning of discrete graphical models and RBM in particular is introduced. Our method, Perturb and Descend (PD) is inspired by two ideas (I) perturb and MAP method for sampling (II) learning by Contrastive Diverge
Externí odkaz:
http://arxiv.org/abs/1405.1436
Autor:
Makhzani, Alireza, Frey, Brendan
Recently, it has been observed that when representations are learnt in a way that encourages sparsity, improved performance is obtained on classification tasks. These methods involve combinations of activation functions, sampling steps and different
Externí odkaz:
http://arxiv.org/abs/1312.5663
Many real-valued stochastic time-series are locally linear (Gassian), but globally non-linear. For example, the trajectory of a human hand gesture can be viewed as a linear dynamic system driven by a nonlinear dynamic system that represents muscle ac
Externí odkaz:
http://arxiv.org/abs/1301.6731