Main Menu (Mobile)- Block
Main Menu - Block
Our research lies at the intersection of neuroscience and computer science. We develop new machine learning methods to map the structure and function of neural circuits.
With recent advances in 3d electron microscopy, optogenetics and large-scale chronic in vivo neural imaging, it is now possible to measure and perturb the activity of large populations of neurons, and to map their connectivity. These new data can be used understand how the structure of a neural circuit gives rise to its function. Our lab develops machine learning algorithms to map neural connectivity, and statistical models to characterize neural activity and to relate activity to connectivity. Check out some of our lab's collaborative work on GitHub.
Projects currently underway include:
- Machine learning algorithms for reconstructing connectomes from electron microscopic images
- Efficient tera-scale machine learning algorithms based on deep neural networks and parallel decision trees
- Statistical models of neural activity and connectivity