-
are developed that prioritize interpretability and reduce data dependency by imposing desirable constraints on model behavior. We will divide our work into three thrusts: Thrust A: A first major objective will be
-
, accurate, and physics-informed machine learning models for predicting blood flow in patient-specific vascular geometries. Current simulation-based approaches require complex 3D meshes and are often too slow
-
on model behavior. We will divide our work into three thrusts: Thrust A: A first major objective will be to augment classical spike train analysis methods particularly those developed by Prof. Grün and
-
regression models to isolate task-related submanifolds and their respective role for sensory processing and task performance Analysis of the data to identify higher-order spike correlations and their temporal
-
submanifolds and their temporal dynamics during behavior Leverage dimensionality reduction and regression models to isolate task-related submanifolds and their respective role for sensory processing and task
-
interpretable, synthesis-proximal modifications to known materials. Create generative models for material discovery adhering to strict physical constraints needed for stable and synthesizable crystal structures