[Eecs_bsee] School of EECS Seminar Series Invited Talk-Advancing the State of the Art and Understanding of Spiking Neural Networks

[Hunter, Tiffany]

Advancing the State of the Art and Understanding of Spiking Neural Networks

Trevor Bihl  trevor.bihl.2 at us.af.mil<mailto:trevor.bihl.2 at us.af.mil>


Davide Manna davide.manna at strath.ac.uk<mailto:davide.manna at strath.ac.uk>

Alex Vicente Sola alex.vicente-sola at strath.ac.uk<mailto:alex.vicente-sola at strath.ac.uk>

Spiking Neural Networks (SNNs) are largely inspired by the human brain and by the theories that govern its components and its learning. Among these, spiking neuron models are used in SNNs to process events coming from Neuromorphic (NM) inputs or propagated within. Neuroscience literature provides a plethora of different spiking neuron models. This talk will consider the neuron models in the literature and present a comparative study aimed at understanding whether using models with different complexities increases the performance of an SNN trained. The relationship between the increased complexity and the richness of the spatio-temporal features of the data is also explored by using two different datasets. Beyond fundamental questions, improving learning algorithms and neural architectures for a more accurate feature extraction are current priorities in SNN research. This talk will further present our recent work on a study on the key components of modern spiking architectures with the developing  a spiking version of the successful residual network (ResNet) architecture.  Our results further outperforms prior SNN architectures in benchmark datasets with less parameters than the prior state of the art.

________________________________________________________________________________
Microsoft Teams meeting
Join on your computer or mobile app
Click here to join the meeting<https://teams.microsoft.com/l/meetup-join/19%3ameeting_NDhjMzNmNzAtYTE5Yy00N2U5LTgyZDMtYTVhYTM0YjlkNzVl%40thread.v2/0?context=%7b%22Tid%22%3a%22f3308007-477c-4a70-8889-34611817c55a%22%2c%22Oid%22%3a%22685c3f4f-29d5-4141-ada5-0fdeab8480e4%22%7d>
Or call in (audio only)
+1 614-706-6572,,89961259#<tel:+16147066572,,89961259#>   United States, Columbus
Phone Conference ID: 899 612 59#
Find a local number<https://dialin.teams.microsoft.com/8f5f7319-0053-4423-a154-4f8b6e7fb7dd?id=89961259> | Reset PIN<https://mysettings.lync.com/pstnconferencing>
[https://www.ohio.edu/sites/default/files/2018-11/invite_logo_teams.jpg]
If you encounter issues with this meeting, please visit the Help link. If you are not able to resolve the problems, please contact the meeting organizer to let them know you are having difficulty.
Learn More<https://aka.ms/JoinTeamsMeeting> | Help<https://www.ohio.edu/oit/services/collaboration/teams/help> | Meeting options<https://teams.microsoft.com/meetingOptions/?organizerId=685c3f4f-29d5-4141-ada5-0fdeab8480e4&tenantId=f3308007-477c-4a70-8889-34611817c55a&threadId=19_meeting_NDhjMzNmNzAtYTE5Yy00N2U5LTgyZDMtYTVhYTM0YjlkNzVl@thread.v2&messageId=0&language=en-US>
________________________________________________________________________________

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://listserv.ohio.edu/pipermail/eecs_bsee/attachments/20220328/eed609d5/attachment.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: text/calendar
Size: 9798 bytes
Desc: not available
URL: <http://listserv.ohio.edu/pipermail/eecs_bsee/attachments/20220328/eed609d5/attachment.ics>