Manifold Computing

We're an open, distributed research group working on significantly improving learning systems and applying them to the toughest problems humanity faces. We do this by advancing theory and also building exceptional open source tools. Read about our vision here .

If you're interested in building the Infrastructure of Intelligence, reach out! 

Explore Our Recent Work

Benchmarking Differentially Private Residual Networks for Medical Imagery

Paper accepted to the ICML Healthcare Systems, Population Health, and Role of Health-Tech Workshop
No dp

Benchmarking Differentially Private Residual Networks for Medical Imagery

Accompanying Poster for our Presentation at the ICML HSYS Workshop
Hnet.com image (1)

Large, Sparse, Multitask Neural Networks

This paper explores various topics and ideas that may prove relevant to large, sparse, multitask networks and explores the potential for a general approach to building and managing these networks.
64051512