655 citations · 2.7k across the 49 of their papers we have counts for
7 papers · 1 filter
Machine learning methods for nanolaser characterization
Darko Zibar, Molly Piels, Ole Winther +2
Nanocavity lasers, which are an integral part of an on-chip integrated photonic network, are setting stringent requirements on the sensitivity of the techniques used to characteriz…
Neural Machine Translation with Characters and Hierarchical Encoding
Alexander Rosenberg Johansen, Jonas Meinertz Hansen, Elias Khazen Obeid +2
Most existing Neural Machine Translation models use groups of characters or whole words as their unit of input and output. We propose a model with a hierarchical char2word encoder,…
Self-Averaging Expectation Propagation
Burak Çakmak, Manfred Opper, Bernard H. Fleury +1
We investigate the problem of approximate Bayesian inference for a general class of observation models by means of the expectation propagation (EP) framework for large systems unde…
Sequential Neural Models with Stochastic Layers
Marco Fraccaro, Søren Kaae Sønderby, Ulrich Paquet +1
How can we efficiently propagate uncertainty in a latent state representation with recurrent neural networks? This paper introduces stochastic recurrent neural networks which glue…
An Adaptive Resample-Move Algorithm for Estimating Normalizing Constants
Marco Fraccaro, Ulrich Paquet, Ole Winther
The estimation of normalizing constants is a fundamental step in probabilistic model comparison. Sequential Monte Carlo methods may be used for this task and have the advantage of…
Auxiliary Deep Generative Models
Lars Maaløe, Casper Kaae Sønderby, Søren Kaae Sønderby +1
Deep generative models parameterized by neural networks have recently achieved state-of-the-art performance in unsupervised and semi-supervised learning. We extend deep generative…
Ladder Variational Autoencoders
Casper Kaae Sønderby, Tapani Raiko, Lars Maaløe +2
Variational Autoencoders are powerful models for unsupervised learning. However deep models with several layers of dependent stochastic variables are difficult to train which limit…