University of Washington Allen School Researchers Develop Machine Learning Technique to Capture the Chatter Between Brain Regions

Researchers led by University of Washington’s Matt Golub developed Multi-Region Latent Factor Analysis via Dynamical Systems (MR-LFADS), a machine learning method that decodes communication between brain regions, even when some are unobserved. The deep learning approach infers hidden neural influences, enabling neuroscientists to better understand how brain regions exchange information that supports sensation, thought, and movement.