We built spiking neural networks that outperform ANNs on event-based vision by initialising them with spatio-temporal receptive fields. Our theory-guided design beats naive approaches by 42%!
New paper in Nature Communications 🧠⚡
Paper (open access): https://www.nature.com/articles/s41467-025-63493-0
Video summary: https://youtu.be/qtHkrx4tYfI
#NeuromorphicComputing #ComputerVision #EventBasedVision
Covariant spatio-temporal receptive fields for spiking neural networks - Nature Communications
Neuromorphic computing mimics brain efficiency but lacks theoretical guidance. Here, authors develop a computational foundation for processing signals in space and time in spiking neural networks that can outperform standard neural networks in event-based vision.
We built spiking neural networks that outperform ANNs on event-based vision by initialising them with spatio-temporal receptive fields. Our theory-guided design beats naive approaches by 42%!
New paper in Nature Communications 🧠⚡
https://www.nature.com/articles/s41467-025-63493-0#NeuromorphicComputing #ComputerVision #EventBasedVisionCovariant spatio-temporal receptive fields for spiking neural networks - Nature Communications
Neuromorphic computing mimics brain efficiency but lacks theoretical guidance. Here, authors develop a computational foundation for processing signals in space and time in spiking neural networks that can outperform standard neural networks in event-based vision.
Very proud of this work of Clément Cabriel, finally published in Nature Photonics!
Event-based vision sensors are here to stay and conquer your hearts and #SMLM microscopes.
Article here: https://www.nature.com/articles/s41566-023-01308-8
Full text access here: https://rdcu.be/dpQhX
#EveSMLM #EventBasedVision
Event-based vision sensor for fast and dense single-molecule localization microscopy - Nature Photonics
Event-based sensors enable super-resolution single-molecule localization microscopy with comparable quality and resolution to traditional scientific cameras, while also overcoming the limitations of high-density imaging.
Jens Egholm
Ignacio Izeddin