-
Trustworthy ML & Robust Statistics
As machine learning systems are pervasively deployed in many scientific fields with increasingly sensitive tasks, it has become paramount to develop algorithms that are robust against the numerous sources of uncertainty inherent in those applications including noise in the data, malicious exploitation of vulnerabilities, outliers, variability of the true objective, privacy, and fairness. While current research in machine learning has led to fundamental breakthroughs, there is still a large gap between the theory and the limitations of the existing algorithms used by practitioners in the real world. An important research direction for our group is to lift the current methods out of the sterile lab environment and scale them into the messy real world, by carefully reexamining their limitations, considering more realistic but less perfect conditions, and developing correspondingly robust algorithms.
-
Collaborative Machine Learning & Federated Learning
The human brain is a complex network of functionally interconnected regions whose coordinated effort gives rise to different functions. Understanding what these regions are, how they interact, and how this interaction forms a wide range of behavior has long been an essential question for human neuroscience. Neuroimaging techniques have provided a unique opportunity to tackle this question in a data-driven way. Advances in neuroimaging techniques, such as functional Magnetic Resonance Imaging (fMRI), have allowed us to approximately measure the neural activity in the brain. However, fMRI data are not only massive in size but also spatially and temporally complex. One of the research directions in our group is to develop advanced machine-learning techniques to study brain function and its link to behavior.
-
Functional Connectivity
The human brain is a complex network of functionally interconnected regions whose coordinated effort gives rise to different functions. Understanding what these regions are, how they interact, and how this interaction forms a wide range of behavior has long been an essential question for human neuroscience. Neuroimaging techniques have provided a unique opportunity to tackle this question in a data-driven way. Advances in neuroimaging techniques, such as functional Magnetic Resonance Imaging (fMRI), have allowed us to approximately measure the neural activity in the brain. However, fMRI data are not only massive in size but also spatially and temporally complex. One of the research directions in our group is to develop advanced machine-learning techniques to study brain function and its link to behavior.