BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Feature Learning with Gradient-Based Methods:Insights from Solvabl
 e Models of Neural Networks
DTSTART:20260313T170000
DTSTAMP:20260403T212140Z
UID:6cd518d1c88b469d00248a24195ead272025f310640bd24a6dc4ebd1
CATEGORIES:Thesis defenses
DESCRIPTION:Luca PESCE\nThesis Director: Prof. F. G. Krzakala\,\nPhysics d
 octoral program\nThesis Nr. 11451\n\nTo take part in the public defense\,
  please contact directly the speaker
LOCATION:MXF 1 https://plan.epfl.ch/?room==MXF%201 https://epfl.zoom.us/j/
 68115022875?pwd=4reo9JRsz9G4mSxrq4AQ1dnUMewCTr.1
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR