Linear Supervised Transfer Learning for Generalized Matrix LVQ

Paaßen B, Schulz A, Hammer B (2016)
In: Proceedings of the Workshop New Challenges in Neural Computation 2016. Hammer B, Martinetz T, Villmann T (Eds); Machine Learning Reports(4). 11-18.

Konferenzbeitrag | Veröffentlicht | Englisch
Herausgeber
; ;
Abstract / Bemerkung
The utility of machine learning models in everyday applications critically depends on their robustness with respect to systematic changes in the input data. However, many machine learning models trained under lab conditions do break down if they are confronted with such systematic changes. Transfer learning addresses this issue by modelling changes in the input as transfer functions, which can be used to map the data to a space where the learned machine learning model is applicable again. In this contribution we introduce linear supervised transfer learning as a novel transfer learning scheme and propose a realization based on generalized matrix learning vector quantization. We evaluate our approach in a practical application from the medical domain, namely classifying the intended arm motion from a muscle signal, which can be used by amputees to control a bionic prosthesis and regain hand function after limb loss.
Erscheinungsjahr
Titel des Konferenzbandes
Proceedings of the Workshop New Challenges in Neural Computation 2016
Zeitschriftennummer
4
Seite
11-18
Konferenz
Workshop New Challenges in Neural Computation (NC^2) 2016
Konferenzort
Hannover
Konferenzdatum
2016-09-12 – 2016-09-12
ISSN
PUB-ID

Zitieren

Paaßen B, Schulz A, Hammer B. Linear Supervised Transfer Learning for Generalized Matrix LVQ. In: Hammer B, Martinetz T, Villmann T, eds. Proceedings of the Workshop New Challenges in Neural Computation 2016. Machine Learning Reports. 2016: 11-18.
Paaßen, B., Schulz, A., & Hammer, B. (2016). Linear Supervised Transfer Learning for Generalized Matrix LVQ. In B. Hammer, T. Martinetz, & T. Villmann (Eds.), Machine Learning Reports. Proceedings of the Workshop New Challenges in Neural Computation 2016 (pp. 11-18).
Paaßen, B., Schulz, A., and Hammer, B. (2016). “Linear Supervised Transfer Learning for Generalized Matrix LVQ” in Proceedings of the Workshop New Challenges in Neural Computation 2016, Hammer, B., Martinetz, T., and Villmann, T. eds. Machine Learning Reports 11-18.
Paaßen, B., Schulz, A., & Hammer, B., 2016. Linear Supervised Transfer Learning for Generalized Matrix LVQ. In B. Hammer, T. Martinetz, & T. Villmann, eds. Proceedings of the Workshop New Challenges in Neural Computation 2016. Machine Learning Reports. pp. 11-18.
B. Paaßen, A. Schulz, and B. Hammer, “Linear Supervised Transfer Learning for Generalized Matrix LVQ”, Proceedings of the Workshop New Challenges in Neural Computation 2016, B. Hammer, T. Martinetz, and T. Villmann, eds., Machine Learning Reports, 2016, pp.11-18.
Paaßen, B., Schulz, A., Hammer, B.: Linear Supervised Transfer Learning for Generalized Matrix LVQ. In: Hammer, B., Martinetz, T., and Villmann, T. (eds.) Proceedings of the Workshop New Challenges in Neural Computation 2016. Machine Learning Reports. p. 11-18. (2016).
Paaßen, Benjamin, Schulz, Alexander, and Hammer, Barbara. “Linear Supervised Transfer Learning for Generalized Matrix LVQ”. Proceedings of the Workshop New Challenges in Neural Computation 2016. Ed. Barbara Hammer, Thomas Martinetz, and Thomas Villmann. 2016. Machine Learning Reports. 11-18.
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
Software:
Beschreibung
Linear Supervised Transfer Learning Toolbox

Export

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Suchen in

Google Scholar