Machine Learning for Exploring Data Streams: Lessons from the VLBA


Wednesday, June 06 2012 - 12:00 pm, PDT
David Thompson
Machine Learning and Instrument Autonomy, JPL

Next-generation science instruments such as the SKA, LSST, and terrestrial sensor networks will dramatically increase the volume of collected data.  This enables detection of very rare transient anomalies, but also creates new challenges since comprehensive storage is impossible and analysis must occur in real time.

Dr. Thompson will discuss machine learning approaches for online anomaly detection in data streams.  Pattern recognition triages the incoming data for comprehensive analysis of candidate events, retaining robustness against changing noise conditions and interferences.  Examples from radio astronomy (the Very Long Baseline Array Fast Transients Experiment) demonstrate the practical benefits of an adaptive approach. 

Other talks you might like:

Video for upcoming talks will be available on this page 3-4 weeks after the talk