A Hybrid Objective Function for Robustness of Artificial Neural Networks -- Estimation of Parameters in a Mechanical System

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.

On decision regions of narrow deep neural networks

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.