Search Results for author:
Found 6 papers, 1 papers with code
Ensembling improves stability and power of feature selection for deep learning models
Despite extensive recent efforts to define different feature importance metrics for deep learning models, we identified that inherent stochasticity in the design and training of deep learning models makes commonly used feature importance scores unstable.
Improving genetic risk prediction across diverse population by disentangling ancestry representations
This can lead to biases in the risk predictors resulting in poor generalization when applied to minority populations and admixed individuals such as African Americans.
Analysis of Discriminator in RKHS Function Space for Kullback-Leibler Divergence Estimation
Based on this theory, we then present a scalable way to control the complexity of the discriminator for a reliable estimation of KL divergence.
Wavelets to the Rescue: Improving Sample Quality of Latent Variable Deep Generative Models
Variational Autoencoders (VAE) are probabilistic deep generative models underpinned by elegant theory, stable training processes, and meaningful manifold representations.
Deep Generative Model with Beta Bernoulli Process for Modeling and Learning Confounding Factors
While deep representation learning has become increasingly capable of separating task-relevant representations from other confounding factors in the data, two significant challenges remain.
Learning disentangled representation from 12-lead electrograms: application in localizing the origin of Ventricular Tachycardia
In this work, we present a conditional variational autoencoder (VAE) to extract the subject-specific adjustment to the ECG data, conditioned on task-specific representations learned from a deterministic encoder.
