This article discusses a research project at the University of Florida (UF) sponsored by the Naval Engineering Education Consortium (NEEC) grant. The project is using information-theoretic techniques to develop a systematic way of understanding machine learning systems. The research is focused on understanding deep learning architectures in military applications and ensuring reliability and proper application of deep learning models. The most current work done under this grant is titled, ‘The Functional Wiener Filter (FWF)’, which extends the Wiener solution for an optimal nonlinear filter to a Reproducing Kernel Hilbert space (RKHS).
