activity
20172022
most citedA Forward-Backward Approach for Visualizing Information Flow in Deep Networks

6 citations · 8 across the 4 of their papers we have counts for

collaborators

7 papers

cs.SD20222 cited

Example-based Explanations with Adversarial Attacks for Respiratory Sound Analysis

Yi Chang, Zhao Ren, Thanh Tam Nguyen +2

Respiratory sound classification is an important tool for remote screening of respiratory-related diseases such as pneumonia, asthma, and COVID-19. To facilitate the interpretabili…

cs.LG2019

Benefits of Jointly Training Autoencoders: An Improved Neural Tangent Kernel Analysis

Thanh V. Nguyen, Raymond K. W. Wong, Chinmay Hegde

A remarkable recent discovery in machine learning has been that deep neural networks can achieve impressive performance (in terms of both lower training error and higher generaliza…

cs.LG2019

BUZz: BUffer Zones for defending adversarial examples in image classification

Kaleel Mahmood, Phuong Ha Nguyen, Lam M. Nguyen +2

We propose a novel defense against all existing gradient based adversarial attacks on deep neural networks for image classification problems. Our defense is based on a combination…

stat.ML2018

Autoencoders Learn Generative Linear Models

Thanh V. Nguyen, Raymond K. W. Wong, Chinmay Hegde

We provide a series of results for unsupervised learning with autoencoders. Specifically, we study shallow two-layer autoencoder architectures with shared weights. We focus on thre…

stat.ML2018

On Learning Sparsely Used Dictionaries from Incomplete Samples

Thanh V. Nguyen, Akshay Soni, Chinmay Hegde

Most existing algorithms for dictionary learning assume that all entries of the (high-dimensional) input data are fully observed. However, in several practical applications (such a…

stat.ML2017

Provably Accurate Double-Sparse Coding

Thanh V. Nguyen, Raymond K. W. Wong, Chinmay Hegde

Sparse coding is a crucial subroutine in algorithms for various signal processing, deep learning, and other machine learning applications. The central goal is to learn an overcompl…