News

Lu Mi defended her thesis “Deep Learning Tools for Next-Generation Connectomics” on August 18, 2022. Check out her slides. Coming soon in Nature! “We are delighted to accept your manuscript entitled “Connectomes across development reveal principles of brain maturation” for publication in Nature. Thank you for choosing to publish your interesting work with us.” #worm, #ai, #connectome. To those who are curious about the details, here is a longer preprint format. July 2021: David Rolnick group ex phd named to the MIT Technology Review’s list of “Innovators Under 35”, and am thrilled to see increasing interest across the AI community in cross-disciplinary partnerships for climateRead More →

Projects

High Throughput Connectomics The current design trend in large scale machine learning is to use distributed clusters of CPUs and GPUs with MapReduce-style programming. Some have been led to believe that this type of horizontal scaling can reduce or even eliminate the need for traditional algorithm development, careful parallelization, and performance engineering. This paper is a case study showing the contrary: that the benefits of algorithms, parallelization, and performance engineering, can sometimes be so vast that it is possible to solve “clusterscale” problems on a single commodity multicore machine. Connectomics is an emerging area of neurobiology that uses cutting edge machine learning and image processingRead More →

Graduate Students

Lu Mi

Jonathan Rosenfeld

Undergraduates

Shraman Ray Chaudhuri
Will Noble

Alumni

David Budden
Jonathan Stoller
Gergely Odor
Victor Jakubiuk
Quan Nguyen
Robert Radway

Publications

Mi, Lu. Deep Learning Tools for Next-Generation Connectomics. PhD thesis, MIT Department of Electrical Engineering and Computer Science, Cambridge, MA., August 2022. Slides. Mi, Lu, Wang, Hao, Tian, Yonglong, He, Hao, Shavit, Nir. Training-Free Uncertainty Estimation for Dense Regression: Sensitivity as a Surrogate. 36th AAAI Conference on Artificial Intelligence- A virtual conference, February 22-March 1, 2022. Mi, Lu, Xu, Richard, Prakhya, Sridhama, Lin, Albert, Shavit, Nir, Samuel, Aravithan D.T. and Turaga, Srinivas C. Connectome-Constrained Latent Variable Models of Whole-Brain Neural Activity. Tenth International Conference on Learning Representations- ICLR 2022 (Virtual), April 2022. Witvliet, Daniel, Mulcahy, Ben, Mitchell, James K., Meirovitch, Yaron, Berger, Daniel R., Wu,Read More →

Resources

No resources yet! But check back in soon.