BEGIN:VCALENDAR
VERSION:2.0
PRODID:-// - ECPv6.15.16//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://www.neuropac.info
X-WR-CALDESC:Events for 
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:UTC
BEGIN:STANDARD
TZOFFSETFROM:+0000
TZOFFSETTO:+0000
TZNAME:UTC
DTSTART:20220101T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:20220313T100000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:20221106T090000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:20230312T100000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:20231105T090000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:20240310T100000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:20241103T090000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;VALUE=DATE:20230309
DTEND;VALUE=DATE:20230315
DTSTAMP:20260727T020436
CREATED:20230129T223003Z
LAST-MODIFIED:20230129T223003Z
UID:10000026-1678320000-1678838399@www.neuropac.info
SUMMARY:Computational and Systems Neuroscience (COSYNE) 2023
DESCRIPTION:The annual COSYNE conference provides an inclusive forum for the exchange of experimental and theoretical approaches to problems in systems neuroscience\, in order to understand how neural systems are built and function.
URL:https://www.neuropac.info/event/computational-and-systems-neuroscience-cosyne-2023/
LOCATION:Montreal\, Montreal\, Canada
CATEGORIES:Conference
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20230314T080000
DTEND;TZID=America/Los_Angeles:20230314T090000
DTSTAMP:20260727T020436
CREATED:20230331T121426Z
LAST-MODIFIED:20230331T121701Z
UID:10000172-1678780800-1678784400@www.neuropac.info
SUMMARY:INRC Forum: Thomas Nowotny
DESCRIPTION:Loss shaping enhances exact gradient learning with EventProp in Spiking Neural Networks\nAbstract: In a recent paper Wunderlich and Pehle (2021) introduced the EventProp algorithm that enables training spiking neural networks by gradient descent on exact gradients. In this talk I will present extensions of EventProp to support a wider class of loss functions and an implementation in the GPU enhanced neuronal networks framework (GeNN) which exploits sparsity. The GPU acceleration allows us to test EventProp extensively on more challenging learning benchmarks. We find that EventProp performs well on some tasks but for others there are issues where learning is slow or fails entirely. We have discovered that the problems relate to the exact gradient of the loss function not providing information about loss changes due to spike creation or spike deletion. Depending on the details of the task and loss function\, descending the exact gradient with EventProp can lead to the deletion of important spikes and so to an inadvertent increase of the loss and decrease of classification accuracy and hence a failure to learn. In other situations\, the lack of knowledge about the benefits of creating additional spikes can lead to a lack of gradient flow into earlier layers\, slowing down learning. We are trying to overcome these problems in the form of `loss shaping’\, where we introduce a suitable weighting function into an integral loss to increase gradient flow from the output layer towards earlier layers. I will show example result for the Spiking Heidelberg Digits and sequential spiking MNIST where we achieve (close to) state-of-the-art performance. \nBio. Prof. Thomas Nowotny has a background in theoretical physics. After his PhD from Leipzig University in 2001 he started working in Computational Neuroscience and bio-inspired AI at the Institute for non-linear Science at UCSD. He is now a Professor in Informatics at the University of Sussex and the head of the AI research group. His interests include olfaction\, hybrid systems\, spiking neural networks and their efficient simulation\, bio-inspired AI and algorithms for neuromorphic computing. \nFor the meeting link\, see the full INRC Forum Spring 2023 Schedule (accessible only to INRC Affiliates and Fully Engaged Members).
URL:https://www.neuropac.info/event/inrc-forum-thomas-nowotny-2/
LOCATION:Online
END:VEVENT
BEGIN:VEVENT
DTSTART;VALUE=DATE:20230315
DTEND;VALUE=DATE:20230316
DTSTAMP:20260727T020436
CREATED:20230225T210608Z
LAST-MODIFIED:20230311T160753Z
UID:10000027-1678838400-1678924799@www.neuropac.info
SUMMARY:Abstract Deadline: International Conference on Neuromorphic\, Natural and Physical Computing
DESCRIPTION:We are happy to announce the “Neuromorphic\, Natural and Physical Computing: Interdisciplinary Foundations (NNPC 2023)”\, organized with generous support by the Volkswagen Foundation. The conference will take place the 25th – 27th of October 2023 in Hanover\, Germany\, and the deadline for submitting a 2-page abstract is March 15th. \nThe general aim of NNPC 2023 is to boost interdisciplinary transfer of ideas and networking in the wider fields of non-digital computing. NNPC 2023 is a successor to the 2018 conference “Cognitive Computing: Merging Concepts with Hardware” (https://nnpc-conference.com/2018) whose very productive and motivating format will be kept\, as well as the location and the generous funding conditions. \nEach session is devoted to a specific theme. We encourage active engagement of attendants by requiring submission of a 2-page abstract on a subject relating to one of the session themes. These abstracts are peer-reviewed. From the accepted abstracts three are chosen for oral presentations and the remaining ones for posters. Importantly\, novelty is not essential as our aim is to make knowledge to diffuse across boundaries of the scientific domains involved.
URL:https://www.neuropac.info/event/abstract-deadline-international-conference-on-neuromorphic-natural-and-physical-computing/
LOCATION:Online
CATEGORIES:Conference,Deadline
END:VEVENT
END:VCALENDAR