kth.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Covariant spatio-temporal receptive fields for neuromorphic computing
KTH, School of Electrical Engineering and Computer Science (EECS), Computer Science, Computational Science and Technology (CST). (Neurocomputing Systems)ORCID iD: 0000-0001-6012-7415
KTH, School of Electrical Engineering and Computer Science (EECS), Computer Science, Computational Science and Technology (CST). (Neurocomputing Systems)ORCID iD: 0000-0001-5998-9640
KTH, School of Electrical Engineering and Computer Science (EECS), Computer Science, Computational Science and Technology (CST). (Computational Vision)ORCID iD: 0000-0002-9081-2170
2024 (English)Report (Other academic)
Abstract [en]

Biological nervous systems constitute important sources of inspiration towards computers that are faster, cheaper, and more energy efficient. Neuromorphic disciplines view the brain as a coevolved system, simultaneously optimizing the hardware and the algorithms running on it. There are clear efficiency gains when bringing the computations into a physical substrate, but we presently lack theories to guide efficient implementations. Here, we present a principled computational model for neuromorphic systems in terms of spatio-temporal receptive fields, based on affine Gaussian kernels over space and leaky-integrator and leaky integrate-and-fire models over time. Our theory is provably covariant to spatial affine and temporal scaling transformations, and with close similarities to the visual processing in mammalian brains. We use these spatio-temporal receptive fields as a prior in an event-based vision task, and show that this improves the training of spiking networks, which otherwise is known as problematic for event-based vision. This work combines efforts within scale-space theory and computational neuroscience to identify theoretically well-founded ways to process spatio-temporal signals in neuromorphic systems. Our contributions are immediately relevant for signal processing and event-based vision, and can be extended to other processing tasks over space and time, such as memory and control.

Place, publisher, year, edition, pages
2024.
Keywords [en]
Scale-space theory, Neuromorphic computing, Computer vision
National Category
Computer Vision and Robotics (Autonomous Systems)
Research subject
Applied and Computational Mathematics
Identifiers
URN: urn:nbn:se:kth:diva-346247DOI: 10.48550/arXiv.2405.00318OAI: oai:DiVA.org:kth-346247DiVA, id: diva2:1856755
Funder
EU, Horizon 2020, 785907Swedish Research Council, 2022-02969EU, Horizon 2020, 945539Swedish Research Council, 2022-0672
Note

QC 20240508

Available from: 2024-05-08 Created: 2024-05-08 Last updated: 2024-05-13Bibliographically approved

Open Access in DiVA

fulltext(2444 kB)40 downloads
File information
File name FULLTEXT01.pdfFile size 2444 kBChecksum SHA-512
e2db969179a096a1077423d2282efd4e8cae96d160099c476991aa82e8749bb2275313be2a350e2ead51e42e38c39bf4c6f7ebdab45137b03dda2faabc27dad1
Type fulltextMimetype application/pdf

Other links

Publisher's full text

Authority records

Pedersen, JensConradt, JörgLindeberg, Tony

Search in DiVA

By author/editor
Pedersen, JensConradt, JörgLindeberg, Tony
By organisation
Computational Science and Technology (CST)
Computer Vision and Robotics (Autonomous Systems)

Search outside of DiVA

GoogleGoogle Scholar
Total: 40 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 373 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf