← Search

Walter Karlen

2 accepted papers

2019

CXPlain: Causal Explanations for Model Interpretation under Uncertainty

NeurIPS 2019poster

Feature importance estimates that inform users about the degree to which given inputs influence the output of a predictive model are crucial for understanding, validating, and interpreting machine-learning models. However, providing fast and accurate estimates of feature importance for high-dimensio…

2018

Not to Cry Wolf: Distantly Supervised Multitask Learning in Critical Care

ICML 2018oral

Patients in the intensive care unit (ICU) require constant and close supervision. To assist clinical staff in this task, hospitals use monitoring systems that trigger audiovisual alarms if their algorithms indicate that a patient’s condition may be worsening. However, current monitoring systems are…