Leveraging advances in variational inference, we propose to enhance recurrent neural networks with latent variables, resulting in Stochastic Recurrent Networks (STORNs). The model i) can be trained with stochastic gradient methods, ii) allows structured and multi-modal conditionals at each time step, iii) features a reliable estimator of the marginal likelihood and iv) is a generalisation of deterministic recurrent neural networks. We evaluate the method on four polyphonic musical data sets and motion capture data.
a b s t r a c t In the last few years, research highlighted the critical role of unsupervised pre-tr...
. Recent work has shown that the extraction of symbolic rules improves the generalization performan...
In the last few years, research highlighted the critical role of unsupervised pre-training strategie...
Leveraging advances in variational inference, we propose to enhance recurrent neural networks with l...
Time series forecasting based on deep architectures has been gaining popularity in recent years due ...
The paper studies a stochastic extension of continuous recurrent neural networks and analyzes gradie...
The ability to learn and perform statistical inference with biologically plausible recurrent network...
Variational methods have been previously explored as a tractable approximation to Bayesian inference...
We present a model for capturing musical features and creating novel sequences of music, called the ...
The paper studies a stochastic extension of continuous recurrent neural networks and analyzes gradie...
Multilayer perceptrons (MLPs) or artificial neural nets are popular models used for non-linear regre...
In this chapter, we describe the basic concepts behind the functioning of recurrent neural networks ...
This study proposes a novel type of dynamic neural network model that can learn to extract stochasti...
We survey learning algorithms for recurrent neural networks with hidden units, and put the various t...
We investigate a novel neural network model which uses stochastic weights. It is shown that the func...
a b s t r a c t In the last few years, research highlighted the critical role of unsupervised pre-tr...
. Recent work has shown that the extraction of symbolic rules improves the generalization performan...
In the last few years, research highlighted the critical role of unsupervised pre-training strategie...
Leveraging advances in variational inference, we propose to enhance recurrent neural networks with l...
Time series forecasting based on deep architectures has been gaining popularity in recent years due ...
The paper studies a stochastic extension of continuous recurrent neural networks and analyzes gradie...
The ability to learn and perform statistical inference with biologically plausible recurrent network...
Variational methods have been previously explored as a tractable approximation to Bayesian inference...
We present a model for capturing musical features and creating novel sequences of music, called the ...
The paper studies a stochastic extension of continuous recurrent neural networks and analyzes gradie...
Multilayer perceptrons (MLPs) or artificial neural nets are popular models used for non-linear regre...
In this chapter, we describe the basic concepts behind the functioning of recurrent neural networks ...
This study proposes a novel type of dynamic neural network model that can learn to extract stochasti...
We survey learning algorithms for recurrent neural networks with hidden units, and put the various t...
We investigate a novel neural network model which uses stochastic weights. It is shown that the func...
a b s t r a c t In the last few years, research highlighted the critical role of unsupervised pre-tr...
. Recent work has shown that the extraction of symbolic rules improves the generalization performan...
In the last few years, research highlighted the critical role of unsupervised pre-training strategie...