Previous Research: Machine Learning in the Hyperbolic Space

Principal Investigator(s): 
Stella Yu

We study how hyperbolic space can be used to facilitate the formation of hierarchical representations from natural data without any supervision.  We demonstrate that hyperbolic neural networks outperform standard  Euclidean counterparts when their optimization process is improved with a restricted feature space, resulting in higher classification performance, more adversarial robustness, and better out-of-distribution detection capability.