Timezone: »

 
Contributed talk: Beyond Sparsity: Tree-based Regularization of Deep Models for Interpretability
Mike Wu · Sonali Parbhoo · Finale Doshi-Velez

Fri Dec 08 10:20 AM -- 10:30 AM (PST) @
in Transparent and interpretable Machine Learning in Safety Critical Environments »

The lack of interpretability remains a key barrier to the adoption of deep models in many healthcare applications. In this work, we explicitly regularize deep models so human users might step through the process behind their predictions in little time. Specifically, we train deep time-series models so their class-probability predictions have high accuracy while being closely modeled by decision trees with few nodes. On two clinical decision-making tasks, we demonstrate that this new tree-based regularization is distinct from simpler L2 or L1 penalties, resulting in more interpretable models without sacrificing predictive power.

Author Information

Mike Wu (Stanford University)
Sonali Parbhoo (University of Basel)
Finale Doshi-Velez (Harvard)

More from the Same Authors