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.

Download
OA 484.94 KB
Conference Paper | Published | English
Editor
Verleysen, Michel
Abstract
Modern bionic hand prostheses feature unprecedented functionality, permitting motion in multiple degrees of freedom (DoFs). However, conventional user interfaces allow for contolling only one DoF at a time. An intuitive, direct and simultaneous control of multiple DoFs requires machine learning models. Unfortunately, such models are not yet sufficiently robust to real-world disturbances, such as electrode shifts. We propose a novel expectation maximization approach for transfer learning to rapidly recalibrate a machine learning model if disturbances occur. In our experimental evaluation we show that even if few data points are available which do not cover all classes, our proposed approach finds a viable transfer mapping which improves classification accuracy significantly and outperforms all tested baselines.
Publishing Year
Conference
25th European Symposium on Artificial Neural Networks (ESANN 2017)
Location
Bruges
Conference Date
2017-04-26 – 2017-04-28
PUB-ID

Cite this

Paaßen B, Schulz A, Hahne J, Hammer B. An EM transfer learning algorithm with applications in bionic hand prostheses. In: Verleysen M, ed. Proceedings of the 25th European Symposium on Artificial Neural Networks (ESANN 2017). Bruges: i6doc.com; 2017: 129-134.
Paaßen, B., Schulz, A., Hahne, J., & Hammer, B. (2017). An EM transfer learning algorithm with applications in bionic hand prostheses. In M. Verleysen (Ed.), Proceedings of the 25th European Symposium on Artificial Neural Networks (ESANN 2017) (pp. 129-134). Bruges: i6doc.com.
Paaßen, B., Schulz, A., Hahne, J., and Hammer, B. (2017). “An EM transfer learning algorithm with applications in bionic hand prostheses” in Proceedings of the 25th European Symposium on Artificial Neural Networks (ESANN 2017), Verleysen, M. ed. (Bruges: i6doc.com), 129-134.
Paaßen, B., et al., 2017. An EM transfer learning algorithm with applications in bionic hand prostheses. In M. Verleysen, ed. Proceedings of the 25th European Symposium on Artificial Neural Networks (ESANN 2017). Bruges: i6doc.com, pp. 129-134.
B. Paaßen, et al., “An EM transfer learning algorithm with applications in bionic hand prostheses”, Proceedings of the 25th European Symposium on Artificial Neural Networks (ESANN 2017), M. Verleysen, ed., Bruges: i6doc.com, 2017, pp.129-134.
Paaßen, B., Schulz, A., Hahne, J., Hammer, B.: An EM transfer learning algorithm with applications in bionic hand prostheses. In: Verleysen, M. (ed.) Proceedings of the 25th European Symposium on Artificial Neural Networks (ESANN 2017). p. 129-134. i6doc.com, Bruges (2017).
Paaßen, Benjamin, Schulz, Alexander, Hahne, Janne, and Hammer, Barbara. “An EM transfer learning algorithm with applications in bionic hand prostheses”. Proceedings of the 25th European Symposium on Artificial Neural Networks (ESANN 2017). Ed. Michel Verleysen. Bruges: i6doc.com, 2017. 129-134.
All files available under the following license(s):
Copyright Statement:
This Item is protected by copyright and/or related rights. [...]
Main File(s)
Access Level
OA Open Access
Last Uploaded
2017-04-27T17:06:44Z

This data publication is cited in the following publications:
This publication cites the following data publications:
2912671
Linear Supervised Transfer Learning Toolbox
Paaßen B, Schulz A (2017) : Bielefeld University. doi:10.4119/unibi/2912671.
Material in PUB:
Popular Science
Linear Supervised Transfer Learning Toolbox
Paaßen B, Schulz A (2017) : Bielefeld University. doi:10.4119/unibi/2912671.
Later Version
Expectation maximization transfer learning and its application for bionic hand prostheses
Paaßen B, Schulz A, Hahne J, Hammer B (In Press)
Neurocomputing.

Export

0 Marked Publications

Open Data PUB

Search this title in

Google Scholar
ISBN Search