
George Stantchev
U.S. Naval Research Laboratory, Washington D.C., USA
deep learning
uncertainty quantification
bayesian methods
model calibration
neuromorphic computing
energy based models
analog neural networks
backpropagation alternatives
2
presentations
SHORT BIO
Dr. George Stantchev received his Ph.D. in Applied Mathematics and Scientific Computation from the University of Maryland at College Park in 2003 and joined NRL as Computer Scientist in 2011. Prior to that he was a Research Scientist at SAIC and a postdoctoral research scientist at the Center for Scientific Computation and Mathematical Modeling (CSCAMM) at the University of Maryland. He has been actively involved in interdisciplinary research on a variety of topics, including electromagnetic modeling and simulation, nonlinear device characterization, machine learning in the RF signal domain, topological data analysis, and decentralized computing for collaborative multi-agent systems. Dr. Stantchev has served as co-organizer of several workshops and symposia on machine learning for cognitive radio communication as well as a Guest Editor of the 2018 Special Issue of the IEEE Journal of Selected Topics in Signal Processing on Machine Learning for Cognition in Radio Communications and Radar. He is the recipient of the NRL Review Award (2014), and the US Department of Navy Alan Berman Publication Award (2016 and 2019).
Presentations

Uncertainty Quantification in Deep Learning
George Stantchev

Energy Based Models for Analog Neural Networks
George Stantchev and 1 other author