activity
20122023
most citedImproving Generalization and Stability of Generative Adversarial Networks

82 citations · 257 across the 26 of their papers we have counts for

collaborators
Showing stat.MLShow all

10 papers · 1 filter

stat.ML20161 cited

Stabilizing Linear Prediction Models using Autoencoder

Shivapratap Gopakumar, Truyen Tran, Dinh Phung +1

To date, the instability of prognostic predictors in a sparse high dimensional model, which hinders their clinical adoption, has received little attention. Stable prediction is oft…

stat.ML20165 cited

Outlier Detection on Mixed-Type Data: An Energy-based Approach

Kien Do, Truyen Tran, Dinh Phung +1

Outlier detection amounts to finding data points that differ significantly from the norm. Classic outlier detection methods are largely designed for single data type such as contin…

stat.ML201610 cited

Preterm Birth Prediction: Deriving Stable and Interpretable Rules from High Dimensional Data

Truyen Tran, Wei Luo, Dinh Phung +3

Preterm births occur at an alarming rate of 10-15%. Preemies have a higher risk of infant mortality, developmental retardation and long-term disabilities. Predicting preterm birth…

stat.ML201628 cited

Deepr: A Convolutional Net for Medical Records

Phuoc Nguyen, Truyen Tran, Nilmini Wickramasinghe +1

Feature engineering remains a major bottleneck when creating predictive systems from electronic medical records. At present, an important missing element is detecting predictive re…

stat.ML2014

MCMC for Hierarchical Semi-Markov Conditional Random Fields

Truyen Tran, Dinh Phung, Svetha Venkatesh +1

Deep architecture such as hierarchical semi-Markov models is an important class of models for nested sequential data. Current exact inference schemes either cost cubic time in sequ…

stat.ML201432 cited

Mixed-Variate Restricted Boltzmann Machines

Truyen Tran, Dinh Phung, Svetha Venkatesh

Modern datasets are becoming heterogeneous. To this end, we present in this paper Mixed-Variate Restricted Boltzmann Machines for simultaneously modelling variables of multiple typ…