Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Carlo Wenig

Carlo Wenig

1 indexed paper

Recent (6 mo)
1
With code
0
Influential cites
0
Benchmarked
0

Publications per year

1
26

Top categories

Neural Computing×1ML×1

Frequent co-authors

Raoul-Martin Memmesheimer1×
Christian Klos1×

Research Timeline

2026
Quadratic integrate-and-fire neurons exhibit less fragmented loss landscapes and outperform leaky integrate-and-fire neurons in spike-based gradient descent

The paper demonstrates that quadratic integrate-and-fire (QIF) neurons are superior to leaky integrate-and-fire (LIF) neurons for gradient descent training in spiking neural networks because their continuous spiking dynamics result in smoother loss landscapes.

Highlighted terms show continued research focus across papers

Papers

cs.NEcs.LGRecentJun 2, 2026

Quadratic integrate-and-fire neurons exhibit less fragmented loss landscapes and outperform leaky integrate-and-fire neurons in spike-based gradient descent

Carlo Wenig, Raoul-Martin Memmesheimer, Christian Klos

The paper demonstrates that quadratic integrate-and-fire (QIF) neurons are superior to leaky integrate-and-fire (LIF) neurons for gradient descent training in spiking neural networks because their con…

View →