Svetha Venkatesh

TL;DR: A framework based on discretization of time into epochs, epoch-wise topic discovery using a hierarchical Dirichlet process-based model, and a temporal similarity graph which allows for the modelling of complex topic changes is proposed.

TL;DR: In this paper, the authors describe a novel framework for the discovery of the topical content of a data corpus, and the tracking of its complex structural changes across the temporal dimension, which does not impose a prior on the rate at which documents are added to the corpus nor does it adopt the Markovian assumption which overly restricts the type of changes that the model can capture.

TL;DR: Resset is an end-to-end recurrent model that reads medical record and predicts future risk, and shows promises in multiple predictive tasks such as readmission prediction, treatments recommendation and diseases progression.

TL;DR: The novelty of the paper lies in the implementation of a scalable framework in the context of both the scale of behaviors and the size of the environment, making it ideal for distributed surveillance.

TL;DR: A new acquisition function is constructed that helps Bayesian optimization to avoid the convergence to the sharp peaks and is guaranteed to prefer stable peaks over unstable ones in the hyperparameter tuning of machine learning models.