(r1) InterOpMay2023KD < IVOA

IVOA Web>WebPreferences>InterOpNov2021>InterOpMay2023KD (revision 1) (raw view)~~EditAttach~~

---++ Knowledge Discovery 1

Time: [[https://www.timeanddate.com/worldclock/fixedtime.html?msg=Apps1&iso=20211103T2200][Wednesday Nov 03 22:00 UTC]]

| *Speaker(s)* | *Title and Abstract* | *Time* | *Material* |
| _Rafael Martinez Galarza_ | <p> *Harvesting outliers: data barriers to turn anomalies into discoveries* </p> <p> </p> <div id="_mcePaste">Over the last few years astronomers have become increasingly effective</div> <div id="_mcePaste">at identifying anomalous objects in large astronomical datasets. So</div> <div id="_mcePaste">far, that has meant "finding objects in sparsely populated regions of</div> <div id="_mcePaste">a multidimensional feature space". This is done using a number of</div> <div id="_mcePaste">methods that includes ensemble methods such as random forests</div> <div id="_mcePaste">searches, and more recently generative models that identify anomalies</div> <div id="_mcePaste">as those objects are more difficult to reconstruct by the trained</div> <div id="_mcePaste">model. This has produced huge lists of anomalies in diverse datasets</div> <div id="_mcePaste">that include SDSS galaxy spectra, Kepler and TESS light curves, and</div> <div id="_mcePaste">X-ray catalogs. Yet, most of those anomalies are not followed up,</div> <div id="_mcePaste">because of a cultural difficulty for scientists to interpret</div> <div id="_mcePaste">multi-dimensional scatter plots that have no labels in their axes. We</div> <div id="_mcePaste">argue that such cultural barrier can be overcome with novel ways to</div> <div id="_mcePaste">combine domain knowledge expertise with data visualization, or even</div> <div id="_mcePaste">incorporating domain knowledge directly into the anomaly detection</div> <div id="_mcePaste">algorithms. We would like to discuss ways in which VO tools can help</div> <div id="_mcePaste">in the identification of anomalies that represent true astronomical</div> <div id="_mcePaste">discoveries, by harvesting the currently publicly available catalogs</div> <div id="_mcePaste">of anomalies.</div> <br /> <p> </p> <p> </p> | 7' | TBD |
| _Petr Skoda_ | <p> *SDSS redshift prediction based on Bayesian Deep Learning* </p> <p> </p> <p> </p> | 7' | TBD |
| _Ashish Mahabal_ | <p> </p> | 7' | TBD |

Moderator: [[IVOA.TBD][TBD]], Notetaker: [[IVOA.TBD][TBD]], [[https://yopad.eu/p/IVOA_Nov21_Apps1][Etherpad link]]

Topic revision: r1 - 2021-10-25 - RaffaeleDAbrusco

IVOA

Log in or Register

IVOA.net
Wiki Home
WebChanges
WebTopicList
WebStatistics

Twiki Meta & Help
IVOA
Know
Main
Sandbox
TWiki

TWiki intro
TWiki tutorial
User registration
Notify me

Working Groups

Interest Groups

Time Domain

Committees

Stds&Procs

www.ivoa.net
Documents
Events
Members
XML Schema