ZED.UCHICAGO.EDU

Our goal is to probe the limits of automated inference, independent of specific applications; when carried out with zero prior knowledge. Our theoretical contributions include data smashing, algorithm GenESeSS , and automated construction of Fractal or Granger Nets - a new approach that is proving effective in predicting complex spatio-temporal phenomena ranging from seismic events across the globe to criminal infractions transpiring in typical urban environments. Exploring the yet unknown possibilities in data science, AI and machine learning, we hope to build inference and reasoning automation that can answer questions that we have not yet thought to ask.