BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Network Features in AI Applications - Lucia Cavallaro (Radboud Un
 iversiteit Nijmegen)
DTSTART:20240813T100000Z
DTEND:20240813T110000Z
UID:TALK219334@talks.cam.ac.uk
DESCRIPTION:This talk shows how Network Science can be applied to miniatur
 ize Artificial Neural Networks (ANNs). More specifically\, an efficient sp
 arsification strategy using Erdős-R&eacute\;nyi random networks to stream
 line the training of ANNs is described. Initial results are promising\, wi
 th Sparse ANNs significantly reduced in size (more than a 75% of sparsity)
  while experiencing minimal accuracy loss. Future research will explore us
 ing Network Science techniques to gain insights into how ANNs operate.\n&n
 bsp\;
LOCATION:External
END:VEVENT
END:VCALENDAR