works on

From the 1 of 6 linked papers with an AI index.

activity
20182022
most citedOn the Origins of the Block Structure Phenomenon in Neural Network Representations

6 citations · 7 across the 2 of their papers we have counts for

collaborators

6 papers

cs.CV20221 cited

A novel deep learning-based approach for sleep apnea detection using single-lead ECG signals

Anh-Tu Nguyen, Thao Nguyen, Huy-Khiem Le +2

Sleep apnea (SA) is a type of sleep disorder characterized by snoring and chronic sleeplessness, which can lead to serious conditions such as high blood pressure, heart failure, an…

cs.LG20226 cited

On the Origins of the Block Structure Phenomenon in Neural Network Representations

Thao Nguyen, Maithra Raghu, Simon Kornblith

Recent work has uncovered a striking phenomenon in large-capacity neural networks: they contain blocks of contiguous hidden layers with highly similar representations. This block s…

cs.LG2020

Do Wide and Deep Networks Learn the Same Things? Uncovering How Neural Network Representations Vary with Width and Depth

Thao Nguyen, Maithra Raghu, Simon Kornblith

A key factor in the success of deep neural networks is the ability to scale models to improve performance by varying the architecture depth and width. This simple property of neura…

cs.LG2020

Concept Bottleneck Models

Pang Wei Koh, Thao Nguyen, Yew Siang Tang +4

We seek to learn models that we can interact with using high-level concepts: if the model did not think there was a bone spur in the x-ray, would it still predict severe arthritis?…

cs.LG2018

Predicting Inpatient Discharge Prioritization With Electronic Health Records

Anand Avati, Stephen Pfohl, Chris Lin +7

The paper develops machine‑learning models using eight years of Stanford Hospital electronic health records to predict which inpatients will be discharged within the next 24 hours,…

cs.CR2018

A Fully Private Pipeline for Deep Learning on Electronic Health Records

Edward Chou, Thao Nguyen, Josh Beal +2

We introduce an end-to-end private deep learning framework, applied to the task of predicting 30-day readmission from electronic health records. By using differential privacy durin…