61 citations · 321 across the 27 of their papers we have counts for
5 papers · 1 filter
Shapley Flow: A Graph-based Approach to Interpreting Model Predictions
Jiaxuan Wang, Jenna Wiens, Scott Lundberg
Many existing approaches for estimating feature importance are problematic because they ignore or hide dependencies among features. A causal graph, which encodes the relationships…
Deep Learning Applied to Chest X-Rays: Exploiting and Preventing Shortcuts
Sarah Jabbour, David Fouhey, Ella Kazerooni +2
While deep learning has shown promise in improving the automated diagnosis of disease based on chest X-rays, deep networks may exhibit undesirable behavior related to shortcuts. Th…
Deep Reinforcement Learning for Closed-Loop Blood Glucose Control
Ian Fox, Joyce Lee, Rodica Pop-Busui +1
People with type 1 diabetes (T1D) lack the ability to produce the insulin their bodies need. As a result, they must continually make decisions about how much insulin to self-admini…
Clinician-in-the-Loop Decision Making: Reinforcement Learning with Near-Optimal Set-Valued Policies
Shengpu Tang, Aditya Modi, Michael W. Sjoding +1
Standard reinforcement learning (RL) aims to find an optimal policy that identifies the best action for each state. However, in healthcare settings, many actions may be near-equiva…
AdaSGD: Bridging the gap between SGD and Adam
Jiaxuan Wang, Jenna Wiens
In the context of stochastic gradient descent(SGD) and adaptive moment estimation (Adam),researchers have recently proposed optimization techniques that transition from Adam to SGD…