Research
By the end of this year, roughly 1.5 million children in the United States will be living with autism, more than 50,000 young adults will suffer their first schizophrenic break, close to 795,000 individuals will have stroke, nearly 18 million people will go through a major depressive episode, and over 6 million older adults will manifest the early signs of Alzheimer’s disease.
The Neural Systems Analysis Laboratory (NSA Lab) at Boston University develops new AI algorithms that harness the power of noninvasive neuroimaging, electrophysiology, and genetics data to better understand and treat brain disorders. Our strategy is to combine hypothesis-driven insights about the brain with data-driven learning techniques; this combination provides interpretable and actionable information while retaining predictive power. We have developed a range of analytical tools that include purely generative models, deep neural network architectures, and deep-generative hybrid models that trade off structure and flexibility on smaller datasets. We have also built a wide portfolio of collaborative projects that span the “scientific spectrum”, from answering foundational neuroscience questions to translational applications of multimodal data to exploratory directions for probing neural circuitry.
