
HyperVAE: A Minimum Description Length Variational HyperEncoding Network
We propose a framework called HyperVAE for encoding distributions of dis...
read it

Memorizing Normality to Detect Anomaly: Memoryaugmented Deep Autoencoder for Unsupervised Anomaly Detection
Deep autoencoder has been extensively used for anomaly detection. Traini...
read it

Improving Generalization and Stability of Generative Adversarial Networks
Generative Adversarial Networks (GANs) are one of the most popular tools...
read it

Distributionally Robust Bayesian Quadrature Optimization
Bayesian quadrature optimization (BQO) maximizes the expectation of an e...
read it

Learning Transferable Domain Priors for Safe Exploration in Reinforcement Learning
Prior access to domain knowledge could significantly improve the perform...
read it

SelfAssttentive Associative Memory
Heretofore, neural networks with external memory are restricted to singl...
read it

Bayesian Optimization for Categorical and CategorySpecific Continuous Inputs
Many realworld functions are defined over both categorical and category...
read it

SelfAttentive Associative Memory
Heretofore, neural networks with external memory are restricted to singl...
read it

Bayesian functional optimisation with shape prior
Real world experiments are expensive, and thus it is important to reach ...
read it

Learning Regularity in Skeleton Trajectories for Anomaly Detection in Videos
Appearance features have been widely used in video anomaly detection eve...
read it

Graph Transformation Policy Network for Chemical Reaction Prediction
We address a fundamental problem in chemistry known as chemical reaction...
read it

Hierarchical Conditional Relation Networks for Video Question Answering
Video question answering (VideoQA) is challenging as it requires modelin...
read it

Dynamic Language Binding in Relational Visual Reasoning
We present Languagebinding Object Graph Network, the first neural reaso...
read it

Learning to Remember More with Less Memorization
Memoryaugmented neural networks consisting of a neural controller and a...
read it

Learning to Reason with Relational Video Representation for Question Answering
How does machine learn to reason about the content of a video in answeri...
read it

Incorporating Expert Prior Knowledge into Experimental Design via Posterior Sampling
Scientific experiments are usually expensive due to complex experimental...
read it

Incorporating Expert Prior in Bayesian Optimisation via Space Warping
Bayesian optimisation is a wellknown sampleefficient method for the op...
read it

On catastrophic forgetting and mode collapse in Generative Adversarial Networks
Generative Adversarial Networks (GAN) are one of the most prominent tool...
read it

Statistical Latent Space Approach for Mixed Data Modelling and Applications
The analysis of mixed data has been raising challenges in statistics and...
read it

Graph Classification via Deep Learning with Virtual Nodes
Learning representation for graph classification turns a variablesize g...
read it

Deep Learning to Attend to Risk in ICU
Modeling physiological timeseries in ICU is of high clinical importance...
read it

One Size Fits Many: Column Bundle for MultiX Learning
Much recent machine learning research has been directed towards leveragi...
read it

Stabilizing Linear Prediction Models using Autoencoder
To date, the instability of prognostic predictors in a sparse high dimen...
read it

Column Networks for Collective Classification
Relational learning deals with data that are characterized by relational...
read it

Outlier Detection on MixedType Data: An Energybased Approach
Outlier detection amounts to finding data points that differ significant...
read it

Faster Training of Very Deep Networks Via pNorm Gates
A major contributing factor to the recent advances in deep neural networ...
read it

Preterm Birth Prediction: Deriving Stable and Interpretable Rules from High Dimensional Data
Preterm births occur at an alarming rate of 1015 risk of infant mortali...
read it

Deepr: A Convolutional Net for Medical Records
Feature engineering remains a major bottleneck when creating predictive ...
read it

An evaluation of randomized machine learning methods for redundant data: Predicting short and mediumterm suicide risk from administrative records and risk assessments
Accurate prediction of suicide risk in mental health patients remains an...
read it

Choice by Elimination via Deep Neural Networks
We introduce Neural Choice by Elimination, a new framework that integrat...
read it

Collaborative filtering via sparse Markov random fields
Recommender systems play a central role in providing individualized acce...
read it

DeepCare: A Deep Dynamic Memory Model for Predictive Medicine
Personalized predictive medicine necessitates the modeling of patient il...
read it

Achieving stable subspace clustering by postprocessing generic clustering results
We propose an effective subspace selection scheme as a postprocessing s...
read it

Learning deep representation of multityped objects and tasks
We introduce a deep multitask architecture to integrate multityped repre...
read it

MCMC for Hierarchical SemiMarkov Conditional Random Fields
Deep architecture such as hierarchical semiMarkov models is an importan...
read it

MixedVariate Restricted Boltzmann Machines
Modern datasets are becoming heterogeneous. To this end, we present in t...
read it

Thurstonian Boltzmann Machines: Learning from Multiple Inequalities
We introduce Thurstonian Boltzmann Machines (TBM), a unified architectur...
read it

Cumulative Restricted Boltzmann Machines for Ordinal Matrix Data Analysis
Ordinal data is omnipresent in almost all multiusergenerated feedback ...
read it

Learning From Ordered Sets and Applications in Collaborative Ranking
Ranking over sets arise when users choose between groups of items. For e...
read it

Permutation Models for Collaborative Ranking
We study the problem of collaborative filtering where ranking informatio...
read it

Stabilizing Sparse Cox Model using Clinical Structures in Electronic Medical Records
Stability in clinical prediction models is crucial for transferability b...
read it

Learning Rank Functionals: An Empirical Study
Ranking is a key aspect of many applications, such as information retrie...
read it

Bayesian Nonparametric Multilevel Clustering with GroupLevel Contexts
We present a Bayesian nonparametric framework for multilevel clustering ...
read it

The adaptable buffer algorithm for high quantile estimation in nonstationary data streams
The need to estimate a particular quantile of a distribution is an impor...
read it

Groupwise registration of aerial images
This paper addresses the task of time separated aerial image registratio...
read it

Viewpoint distortion compensation in practical surveillance systems
Our aim is to estimate the perspectiveeffected geometric distortion of ...
read it

Efficient algorithms for robust recovery of images from compressed data
Compressed sensing (CS) is an important theory for subNyquist sampling ...
read it

Boosted Markov Networks for Activity Recognition
We explore a framework called boosted Markov networks to combine the lea...
read it

Human Activity Learning and Segmentation using Partially Hidden Discriminative Models
Learning and understanding the typical patterns in the daily activities ...
read it

Learning Structured Outputs from Partial Labels using Forest Ensemble
Learning structured outputs with general structures is computationally c...
read it
Svetha Venkatesh
is this you? claim profile
Australian Laureate Fellow Alfred Deakin Professor and Director Center for Pattern Recognition and Data Analytics (PRaDA) at Deakin University