In 2017, DARPA's Information Innovation Office (I2O) incorporated Deep Learning Analytics' image manifold work into their "A DARPA Perspective on Artificial Intelligence."The video notes here (approved for public release) outline the process and illustrate how simple tSNE embeddings can capture image manifold properties (like look angle loops) in embeddings. If missing data gaps on data manifolds are easier to identify in lower dimensional embeddings, it may also inform research on deep learning methods to improve inference performance in domains with limited training data.
Deep Learning Analytics Featured in Rosslyn Business Improvement District's Newsletter
March 30, 2017
Deep Learning Analytics Develops DARPA Deep Machine Learning Prototype
May 11, 2016
Jenn Sleeman, of Deep Learning Analytics, Recognized as one of the Best Data Scientists in the Washington region