Gregory Byrne
Leidos
machine learning
beamforming
signal processing
acoustics
interpretable
magnetic anomaly detection
masint
passive sonar
signal augmentation
machine learning generalization
machine learning training
3
presentations
2
citations
SHORT BIO
Dr. Gregory Byrne, Principal Machine Learning Scientist, Applied Science Division, Leidos Innovations Center (LInC). Dr. Byrne holds a BS in Physics (Drexel) and a Ph.D. in Computational Fluid Dynamics (GMU) with Postdoctoral Fellowships from Georgia Tech and Stonybrook Universities. Dr. Byrne has 15 years’ experience in high performance computing, physics-based modeling and simulation, dynamical systems theory, machine learning and applied math. He has served as principal investigator and/or tech lead across a diverse set of machine learning programs at Leidos involving Radio Frequency, Electronic Warfare, Geophysics, Magnetic Anomaly Detection and Maritime Acoustic applications.
Presentations
Adversarial Machine Learning Training for Signal-to-Noise Generalization in Passive Undersea Acoustics
Ian Whitehouse and 1 other author
An End-to-end Neural Network for Acoustic Source Detection and Classification on a Linear Sensor Array
Gregory Byrne and 1 other author
Time-Domain Neural Network Detects Passing Dipole Targets Registered by a Magnetic Vector Gradiometer
Gregory Byrne and 1 other author