29 citations · 103 across the 24 of their papers we have counts for
7 papers · 1 filter
Wavelets to the Rescue: Improving Sample Quality of Latent Variable Deep Generative Models
Prashnna K Gyawali, Rudra Saha, Linwei Wang +2
Variational Autoencoders (VAE) are probabilistic deep generative models underpinned by elegant theory, stable training processes, and meaningful manifold representations. However,…
Improving Disentangled Representation Learning with the Beta Bernoulli Process
Prashnna Kumar Gyawali, Zhiyuan Li, Cameron Knight +4
To improve the ability of VAE to disentangle in the latent space, existing works mostly focus on enforcing independence among the learned latent factors. However, the ability of th…
Semi-Supervised Learning by Disentangling and Self-Ensembling Over Stochastic Latent Space
Prashnna Kumar Gyawali, Zhiyuan Li, Sandesh Ghimire +1
The success of deep learning in medical imaging is mostly achieved at the cost of a large labeled data set. Semi-supervised learning (SSL) provides a promising solution by leveragi…
Bayesian Optimization on Large Graphs via a Graph Convolutional Generative Model: Application in Cardiac Model Personalization
Jwala Dhamala, Sandesh Ghimire, John L. Sapp +2
Personalization of cardiac models involves the optimization of organ tissue properties that vary spatially over the non-Euclidean geometry model of the heart. To represent the high…
A Variational Approach to Sparse Model Error Estimation in Cardiac Electrophysiological Imaging
Sandesh Ghimire, John L Sapp, Milan Horacek +1
Noninvasive reconstruction of cardiac electrical activity from surface electrocardiograms (ECG) involves solving an ill-posed inverse problem. Cardiac electrophysiological (EP) mod…
Generative Modeling and Inverse Imaging of Cardiac Transmembrane Potential
Sandesh Ghimire, Jwala Dhamala, Prashnna Kumar Gyawali +3
Noninvasive reconstruction of cardiac transmembrane potential (TMP) from surface electrocardiograms (ECG) involves an ill-posed inverse problem. Model-constrained regularization is…