Project P1 develops conditional independence tests for structured data, such as images in particular, by using Deep Learning (DL) for data embedding and combining it with tests in random effect models. By doing so, we can reduce the parametric assumptions of current tests, boost statistical power compared to fixed-effects tests, and enable conditioning on covariates or confounders.
The tests for conditional independence will be used as input for visual explanation tests in P2, and they will also be applied in P4 and P7.