68 citations · 87 across the 9 of their papers we have counts for
Showing 2019Show all
3 papers · 1 filter
cs.LG2019★ 68 cited
Hidden Unit Specialization in Layered Neural Networks: ReLU vs. Sigmoidal Activation
Elisa Oostwal, Michiel Straat, Michael Biehl
We study layered neural networks of rectified linear units (ReLU) in a modelling framework for stochastic training processes. The comparison with sigmoidal activation functions is…
eess.IV2019★ 1 cited
Segmentation of blood vessels in retinal fundus images
Michiel Straat, Jorrit Oosterhof
In recent years, several automatic segmentation methods have been proposed for blood vessels in retinal fundus images, ranging from using cheap and fast trainable filters to compli…
cs.LG2019★ 5 cited
On-line learning dynamics of ReLU neural networks using statistical physics techniques
Michiel Straat, Michael Biehl
We introduce exact macroscopic on-line learning dynamics of two-layer neural networks with ReLU units in the form of a system of differential equations, using techniques borrowed f…