Dr. Hannes Stuke (Freie Universität Berlin)
Tuesday, November 13, 2018 - 14:15
Technische Universität Berlin
Straße des 17. Juni 136,, 10623 Berlin, MA415
We consider a typical problem of machine learning - the reconstruction of probability distributions of observed data. We introduce the so-called gradient conjugate prior (GCP) update and study the induced dynamical system. We will explain the dynamics of the parameters and show how one can use insights from the dynamical behavior to recover the ground truth distribution in a way that is more robust against outliers. The developed approach also carries over to neural networks.
submitted by Patricia H (patricia.habasescu@fu-berlin.de)