Expectation maximization transfer learning and its application for bionic hand prostheses

Paaßen B, Schulz A, Hahne J, Hammer B (2018)
Neurocomputing 298: 122-133.

Zeitschriftenaufsatz | Veröffentlicht | Englisch
Abstract / Bemerkung
Machine learning models in practical settings are typically confronted with changes to the distribution of the incoming data. Such changes can severely affect the model performance, leading for example to misclassifications of data. This is particularly apparent in the domain of bionic hand prostheses, where machine learning models promise faster and more intuitive user interfaces, but are hindered by their lack of robustness to everyday disturbances, such as electrode shifts. One way to address changes in the data distribution is transfer learning, that is, to transfer the disturbed data to a space where the original model is applicable again. In this contribution, we propose a novel expectation maximization algorithm to learn linear transformations that maximize the likelihood of disturbed data after the transformation. We also show that this approach generalizes to discriminative models, in particular learning vector quantization models. In our evaluation on data from the bionic prostheses domain we demonstrate that our approach can learn a transformation which improves classification accuracy significantly and outperforms all tested baselines, if few data or few classes are available in the target domain.
Erscheinungsjahr
Zeitschriftentitel
Neurocomputing
Band
298
Seite
122-133
ISSN
PUB-ID

Zitieren

Paaßen B, Schulz A, Hahne J, Hammer B. Expectation maximization transfer learning and its application for bionic hand prostheses. Neurocomputing. 2018;298:122-133.
Paaßen, B., Schulz, A., Hahne, J., & Hammer, B. (2018). Expectation maximization transfer learning and its application for bionic hand prostheses. Neurocomputing, 298, 122-133. doi:10.1016/j.neucom.2017.11.072
Paaßen, B., Schulz, A., Hahne, J., and Hammer, B. (2018). Expectation maximization transfer learning and its application for bionic hand prostheses. Neurocomputing 298, 122-133.
Paaßen, B., et al., 2018. Expectation maximization transfer learning and its application for bionic hand prostheses. Neurocomputing, 298, p 122-133.
B. Paaßen, et al., “Expectation maximization transfer learning and its application for bionic hand prostheses”, Neurocomputing, vol. 298, 2018, pp. 122-133.
Paaßen, B., Schulz, A., Hahne, J., Hammer, B.: Expectation maximization transfer learning and its application for bionic hand prostheses. Neurocomputing. 298, 122-133 (2018).
Paaßen, Benjamin, Schulz, Alexander, Hahne, Janne, and Hammer, Barbara. “Expectation maximization transfer learning and its application for bionic hand prostheses”. Neurocomputing 298 (2018): 122-133.
Alle Dateien verfügbar unter der/den folgenden Lizenz(en):
Copyright Statement:
This Item is protected by copyright and/or related rights. [...]
Link(s) zu Volltext(en)
Access Level
OA Open Access
Material in PUB:
Frühere Version
An EM transfer learning algorithm with applications in bionic hand prostheses
Paaßen B, Schulz A, Hahne J, Hammer B (2017)
In: Proceedings of the 25th European Symposium on Artificial Neural Networks (ESANN 2017). Verleysen M (Ed); Bruges: i6doc.com: 129-134.

Export

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Web of Science

Dieser Datensatz im Web of Science®

Quellen

arXiv: 1711.09256

Suchen in

Google Scholar