3 papers
stat.ML2017
Robust Unsupervised Domain Adaptation for Neural Networks via Moment Alignment
Werner Zellinger, Bernhard A. Moser, Thomas Grubinger +3
A novel approach for unsupervised domain adaptation for neural networks is proposed. It relies on metric-based regularization of the learning process. The metric-based regularizati…
stat.ML2017
Central Moment Discrepancy (CMD) for Domain-Invariant Representation Learning
Werner Zellinger, Thomas Grubinger, Edwin Lughofer +2
The learning of domain-invariant representations in the context of domain adaptation with neural networks is considered. We propose a new regularization method that minimizes the d…
eess.SY2016
Generalized Online Transfer Learning for Climate Control in Residential Buildings
Thomas Grubinger, Georgios Chasparis, Thomas Natschlaeger
This paper presents an online transfer learning framework for improving temperature predictions in residential buildings. In transfer learning, prediction models trained under a se…