BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//une sortie//unesortie.fr//FR
CALSCALE:GREGORIAN
BEGIN:VEVENT
UID:52e78d39-ace6-457d-bd7c-a5905d0e7d75@unesortie.fr
DTSTAMP:20261031T221500Z
SUMMARY:CVN+MICS Seminar: Srinivasan Parthasarathy
DTSTART:20261104T090000Z
DTEND:20261104T100000Z
LOCATION:Amphi V\, Bâtiment Eiffel\, CentraleSupélec · 3 rue Joliot Curi
 e\, 91190 Gif-sur-Yvette
DESCRIPTION:Abstract Deep electrocardiogram (ECG) classifiers achieve impre
 ssive performance in detecting cardiac conditions\; however\, they often o
 bscure the specific waveform regions that influence their predictions. To 
 balance classification accuracy with clinical transparency\, we present LY
 NX-ECG\, a hierarchical visibility graph neural network that links key poi
 nts on the time series based on geometric visibility. By preserving import
 ant morphological and timing anchors while significantly reducing stora…
 \n\nhttps://unesortie.fr/e/cvnmics-seminar-srinivasan-parthasarathy-52e78d
 /
URL:https://unesortie.fr/e/cvnmics-seminar-srinivasan-parthasarathy-52e78d/
END:VEVENT
END:VCALENDAR