BEGIN:VCALENDAR
VERSION:2.0
PRODID:researchseminars.org
CALSCALE:GREGORIAN
X-WR-CALNAME:researchseminars.org
BEGIN:VEVENT
SUMMARY:Martina Scolamiero (KTH Royal Institute of Technology - Sweden)
DTSTART:20220902T150000Z
DTEND:20220902T160000Z
DTSTAMP:20260423T022934Z
UID:GEOTOP-A/22
DESCRIPTION:Title: <a href="https://researchseminars.org/talk/GEOTOP-A/22/
 ">Stable and interpretable topological feature maps</a>\nby Martina Scolam
 iero (KTH Royal Institute of Technology - Sweden) as part of GEOTOP-A semi
 nar\n\n\nAbstract\nPersistent homology\, a popular method in TDA\, can be 
 used to define feature maps encoding geometrical properties of data. In th
 is talk I will present a method\, developed by the TDA group at KTH\, whic
 h allows to construct feature maps with learnable parameters\, stable with
  respect to distances on persistence modules. The feature maps are in fact
  defined starting from distances between persistence modules rather than o
 n the barcode decomposition\, making the method suitable for generalisatio
 ns. Particular focus will be on understanding parametrised families of suc
 h feature maps\, such as those stable with respect to p-Wasserstein distan
 ce. The use of Wasserstein stable features will be illustrated on real wor
 ld and artificial datasets.\n
LOCATION:https://researchseminars.org/talk/GEOTOP-A/22/
END:VEVENT
END:VCALENDAR