"Diving For Treasure In Complex Data "


Marvin Weinstein , Stanford University
[Host: Simonetta Liuti]
ABSTRACT:
All fields of scientific research have experienced an explosion of data. It is a formidable computational challenge to analyze this data to extract unexpected patterns. Meeting this challenge will require new, advanced methods of analysis. Dynamic Quantum Clustering is such a tool. The algorithm, invented by David Horn (Tel Aviv University) and myself, provides a highly visual and interactive tool that allows one to explore complicated data that has unknown structure. My talk will provide a brief introduction to the distinction between supervised and unsupervised methods in data mining (clustering in particular). Then, I will, very briefly, discuss the theory of DQC. The bulk of my talk will be devoted to showing results on a data set coming from the Stanford Synchrotron Radiation Laboratory and some results from data on earthquakes in the Middle East. These examples show the power of DQC applied to data sets on which the currently most favored unsupervised data mining techniques fail to obtain any interesting results. The message will be that large, complex, data sets typically exhibit extended structures that are significant and that cannot be seen by other methods.
SLIDESHOW:
Colloquium
Thursday, October 27, 2011
4:00 PM
Physics Building, Room 204
Note special date.
Note special time.
Note special room.

Special Colloquium


 Slideshow (PDF)
 Add to your calendar

To add a speaker, send an email to phys-speakers@Virginia.EDU. Please include the seminar type (e.g. Colloquia), date, name of the speaker, title of talk, and an abstract (if available).