SCHNEIDER: System for Counterfactual Human Network Evaluation of Individual Differences, Errors, and Residuals
Funding Agency: Defense Advanced Research Projects Agency (DARPA)
Collaborators: Jeremy Gottlieb (PI) & Sonja Schmer-Galunder (co-PI)
SCHNEIDER will apply ABM and probabilistic reasoning to the problem of modeling human performance. In particular, it will capture the full distribution of human measurements by representing possibilities outside the “average” range probabilistically, such that they can still be reasoned about and appropriate decisions about interventions made. Thus, these models will be more sensitive to individual differences and more robust to a wider range of people, behaviors, and contexts.