We are not able to deal with a mammoth text corpus without summarizing them into a
relatively small subset. A computational tool is extremely needed to understand such a …

Many modern unsupervised or semi-supervised machine learning algorithms rely on
Bayesian probabilistic models. These models are usually intractable and thus require …

We present a system for training deep neural networks for object detection using synthetic
images. To handle the variability in real-world data, the system relies upon the technique of …

Topic modeling is one of the most powerful techniques in text mining for data mining, latent
data discovery, and finding relationships among data and text documents. Researchers …

We propose a new regularization method based on virtual adversarial loss: a new measure
of local smoothness of the conditional label distribution given input. Virtual adversarial loss …

How can a single person understand what's going on in a collection of millions of
documents? This is an increasingly common problem: sifting through an organization's e …

We develop stochastic variational inference, a scalable algorithm for approximating
posterior distributions. We develop this technique for a large class of probabilistic models …

Social media platforms such as (Twitter, Facebook, and Weibo) are being increasingly
embraced by individuals, groups, and organizations as a valuable source of information …

Managers and researchers alike have long recognized the importance of corporate textual
risk disclosures. Yet it is a nontrivial task to discover and quantify variables of interest from …

Topic modeling is a type of statistical model for discovering the latent “topics” that occur in a
collection of documents through machine learning. Currently, latent Dirichlet allocation …