Pixel Club: Empirical Intrinsic Geometries of Stochastic Datasets

Ronald Coifman (Mathematics and Computer Science, Yale)
Tuesday, 19.11.2013, 11:30
EE Meyer Building 1003

We will provide and overview of a range of ideas from Analysis, Statistical learning and diffusion Geometry , which address the transition from local data models to global configurations. In particular if the data under consideration is sensor data which is a noisy nonlinear complex transformation of natural parameters , we describe a methodology for deriving these parameters. Specifically we describe the role of eigenvectors (of appropriate locally learned “differential” transformations of histograms) as integration tools. We will show applications to analyze and model EEG signals prior to an epileptic attack , prenatal monitoring , acoustic localization ,molecular dynamics ,chemical reactions etc .

The point being that all models are built with no prior physical knowledge.

Back to the index of events