Learning in the Model Space of Neural Networks

Aswolinskiy W (2018)
Bielefeld: Universität Bielefeld.

Bielefelder E-Dissertation | Englisch
 
Download
OA 8.70 MB
Abstract / Bemerkung
Learning from time series is in demand in many domains including finance, medicine and industry. Recently, a novel method for time series classification was proposed based on the idea of training self-predictive models on the time series and classifying in the space of the learned model parameters - the model space. In this thesis, learning in the model space of neural networks is investigated and extended. First, an empirical investigation of time series classification and clustering in the model space is conducted. Based on experiments on numerous time series datasets, key aspects are identified and improvements proposed. Then, the underlying concept is extended to transfer learning for time series. A novel approach for unsupervised transfer learning using self-predictive modelling is proposed. Finally, a modular framework for modelling parameterized processes is defined. The proposed approaches are successfully validated on synthetic and real-world datasets.
Jahr
2018
Page URI
https://pub.uni-bielefeld.de/record/2916683

Zitieren

Aswolinskiy W. Learning in the Model Space of Neural Networks. Bielefeld: Universität Bielefeld; 2018.
Aswolinskiy, W. (2018). Learning in the Model Space of Neural Networks. Bielefeld: Universität Bielefeld.
Aswolinskiy, W. (2018). Learning in the Model Space of Neural Networks. Bielefeld: Universität Bielefeld.
Aswolinskiy, W., 2018. Learning in the Model Space of Neural Networks, Bielefeld: Universität Bielefeld.
W. Aswolinskiy, Learning in the Model Space of Neural Networks, Bielefeld: Universität Bielefeld, 2018.
Aswolinskiy, W.: Learning in the Model Space of Neural Networks. Universität Bielefeld, Bielefeld (2018).
Aswolinskiy, Witali. Learning in the Model Space of Neural Networks. Bielefeld: Universität Bielefeld, 2018.
Alle Dateien verfügbar unter der/den folgenden Lizenz(en):
Copyright Statement:
Dieses Objekt ist durch das Urheberrecht und/oder verwandte Schutzrechte geschützt. [...]
Volltext(e)
Access Level
OA Open Access
Zuletzt Hochgeladen
2019-09-25T06:52:32Z
MD5 Prüfsumme
c21a0a31064ae62c48b3e05a11b0c5eb

Export

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Suchen in

Google Scholar