We develop scalable algorithms for analysis of complex, high-dimensional data.
Our research focuses on theory and algorithms for extracting actionable information from complex data streams. We are particularly interested in decision-making under uncertainty for autonomy in a variety of application areas. SLI is led by John Fisher
Methods:We develop scalable and robust methods in Bayesian inference, information theory, optimization and machine learning. Of particular interest are Bayesian nonparametrics, information planning, scene understanding, and Bayesian causal inference.
Applications:Applications expose our ideas to the complexity of real world. We collaborate with researchers across the institute and industry partners on a variety oof problems including materials discovery, animal behavior analysis, autonomous systems, and nuclear materials detection.
Sensors:Physics-based sensor models provide robustness and accurate uncertainty quantification in high-stakes sensing applications. We utilize a variety (and growing list) of sensor modalities -- cameras, lidars, RGBd, particle detectors, application-specific sensors -- within our methods.