no code implementations • 12 Jun 2022 • Michiel Straat, Kevin Koster, Nick Goet, Kerstin Bunte
The model achieves an excellent performance (F3-score of 0. 95) predicting material running out of specifications for the tensile strength.
no code implementations • 31 Aug 2020 • Maximilian Münch, Michiel Straat, Michael Biehl, Frank-Michael Schleif
As an information preserving alternative, we propose a complex-valued vector embedding of proximity data.
no code implementations • 21 May 2020 • Michiel Straat, Fthi Abadi, Zhuoyun Kan, Christina Göpfert, Barbara Hammer, Michael Biehl
We present a modelling framework for the investigation of supervised learning in non-stationary environments.
no code implementations • 16 Oct 2019 • Elisa Oostwal, Michiel Straat, Michael Biehl
We study layered neural networks of rectified linear units (ReLU) in a modelling framework for stochastic training processes.
no code implementations • 29 May 2019 • 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 complicated neural networks and even deep learning.
no code implementations • 18 Mar 2019 • 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 from statistical physics.