Projects

VBridge: Support Clinicial Decision-Making with Explainable Machine Learning

VBridge incorporates ML explanations into clinicians' decision-making workflow. Enriched interactions proposed in the system connect the dots between ML features and data to explain healthcare models.

DECE: Explore ML Model with Counterfactual Explanations

DECE supports exploratory visual analysis on ML models with counterfactual explanations. The system helps non-expert users propose, verify, and refine their hypotheses on ML predictions.

ProtoSteer: Interact with Deep Sequence Model through Prototypes

ProtoSteer enables users with little or no ML expertise to improve a deep sequence model by interacting with prototypes.