3 citations · 4 across the 9 of their papers we have counts for
4 papers · 1 filter
Topological properties of basins of attraction and expressiveness of width bounded neural networks
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. We consider…
A Hybrid Objective Function for Robustness of Artificial Neural Networks -- Estimation of Parameters in a Mechanical System
Jan Sokolowski, Volker Schulz, Udo Schröder +1
In several studies, hybrid neural networks have proven to be more robust against noisy input data compared to plain data driven neural networks. We consider the task of estimating…
SVIRO: Synthetic Vehicle Interior Rear Seat Occupancy Dataset and Benchmark
Steve Dias Da Cruz, Oliver Wasenmüller, Hans-Peter Beise +2
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 generali…
Mixing operators with prescribed unimodular eigenvectors
Hans-Peter Beise, Leonhard Frerick, Jürgen Müller
For arbitrary closed countable subsets of the unit circle examples of topologically mixing operators on Hilbert spaces are given which have a densely spanning set of unimodular…