40 citations · 41 across the 3 of their papers we have counts for
3 papers
Training event-based neural networks with exact gradients via Differentiable ODE Solving in JAX
Lukas König, Manuel Kuhn, David Kappel +1
Existing frameworks for gradient-based training of spiking neural networks face a trade-off: discrete-time methods using surrogate gradients support arbitrary neuron models but int…
Understanding Transformer-based Vision Models through Inversion
Jan Rathjens, Shirin Reyhanian, David Kappel +1
Understanding the internal mechanisms of deep neural networks remains a central challenge in machine learning. In computer vision, one promising yet only preliminarily explored app…
Consistently Simulating a Wide Range of Atmospheric Scenarios for K2-18b with a Flexible Radiative Transfer Module
M. Scheucher, F. Wunderlich, J. L. Grenfell +6
The atmospheres of small, potentially rocky exoplanets are expected to cover a diverse range in composition and mass. Studying such objects therefore requires flexible and wide-ran…