Our lab works closely with experimental collaborators to develop machine learning tools that lead to scientific insights

Main Interests

• In the machine learning space, our main interest is developing more interpretable machine learning methods, rather than having methods that work as black boxes.
  
• In the neuroscience space, our main interests are to understand:
  • The interaction between different neural populations (brain areas, cell types, etc)
  • How neural activity flexibly drives behavior across a wide range of conditions
  • How dynamics of neural activity differ across behaviors, diseases, and internal states
    
    

Current Projects

• Developing more interpretable dimensionality reduction techniques to disentangle neural activity related to different neural computations and behaviors.
• Building interpretable decoding models to link neural activity with behavior.
• Creating methods to better understand the interaction between multiple recorded neural populations.