U. Hanebeck

Layer-wise Training of a BNN Based on Progressive Gaussian Filtering

Gaussian Homotopy Optimization with Predictor–Corrector Path Tracking and Deterministic Sampling

A Predictor–Corrector Gaussian Homotopy (PCGH) method is proposed that formulates Gaussian homotopy optimization as a path tracking problem, and geometry-aware arc-length parameterizations based on Fisher-information and Hessian-derived metrics are introduced for efficient approximation of the Gaussian convolution and...

Probabilistic Regression via Neural Network Ensembles

DENSE is an ensemble of multi layer perceptrons (MLPs) that is trained to minimize a modified Cram´er–von Mises distance in the joint space of inputs and outputs that enables non-parametric representations of arbitrary densities without (complex) likelihood design.

Simultaneous Train Localization and Radio Transmitter Mapping with TDoA and Magnetic Field Measurements