Showing cs.LGShow all
3 papers · 1 filter
cs.LG2024
Hyperplane Arrangements and Fixed Points in Iterated PWL Neural Networks
Hans-Peter Beise
We leverage the framework of hyperplane arrangements to analyze potential regions of (stable) fixed points. We provide an upper bound on the number of fixed points for multi-layer…
cs.LG2020
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…
cs.LG2018
On decision regions of narrow deep neural networks
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. The result holds for cont…