We study a variant of the variational autoencoder model (VAE) with a Gaussian mixture as a
prior distribution, with the goal of performing unsupervised clustering through deep …

We rewrite the variational evidence lower bound objective (ELBO) of variational
autoencoders in a way that highlights the role of the encoded data distribution. This …

Probabilistic models with discrete latent variables naturally capture datasets composed of
discrete classes. However, they are difficult to train efficiently, since backpropagation …

A body of recent work in modeling neural activity focuses on recovering low-dimensional
latent features that capture the statistical structure of large-scale neural populations. Most …

Regulating deep neural networks (DNNs) with human structured knowledge has shown to
be of great benefit for improved accuracy and interpretability. We develop a general …

Latent generative models can learn higher-level underlying factors from complex data in an
unsupervised manner. Such models can be used in a wide range of speech processing …

In this work, we present the first results for neuralizing an Unsupervised Hidden Markov
Model. We evaluate our approach on tag in-duction. Our approach outperforms existing …

Many natural systems, such as neurons firing in the brain or basketball teams traversing a
court, give rise to time series data with complex, nonlinear dynamics. We can gain insight …

Advances in neural variational inference have facilitated the learning of powerful directed
graphical models with continuous latent variables, such as variational autoencoders. The …

Abstract Factorial Hidden Markov Models (FHMMs) are powerful models for sequential data
but they do not scale well with long sequences. We propose a scalable inference and …