no code implementations • 10 Nov 2020 • Hans-Peter Beise, Steve Dias Da Cruz
In Radhakrishnan et al. [2020], the authors empirically show that autoencoders trained with usual SGD methods shape out basins of attraction around their training data.
no code implementations • 16 Apr 2020 • Jan Sokolowski, Volker Schulz, Udo Schröder, Hans-Peter Beise
We introduce a convolutional neural network architecture that given sequential data predicts the parameters of the underlying data's dynamics.
1 code implementation • 10 Jan 2020 • Steve Dias Da Cruz, Oliver Wasenmüller, Hans-Peter Beise, Thomas Stifter, Didier Stricker
We release SVIRO, a synthetic dataset for sceneries in the passenger compartment of ten different vehicles, in order to analyze machine learning-based approaches for their generalization capacities and reliability when trained on a limited number of variations (e. g. identical backgrounds and textures, few instances per class).
no code implementations • 3 Jul 2018 • Hans-Peter Beise, Steve Dias Da Cruz, Udo Schröder
We show that for neural network functions that have width less or equal to the input dimension all connected components of decision regions are unbounded.