| Publikationstyp: | Beitrag in wissenschaftlicher Zeitschrift |
| Art der Begutachtung: | Keine Angabe |
| Titel: | Context-aware learning for generative models |
| Autor/-in: | Perdikis, Serafeim Leeb, Robert Chavarriaga, Ricardo Millán, José del R. |
| et. al: | No |
| DOI: | 10.1109/TNNLS.2020.3011671 |
| Erschienen in: | IEEE Transactions on Neural Networks and Learning Systems |
| Erscheinungsdatum: | 10-Aug-2020 |
| Verlag / Hrsg. Institution: | IEEE |
| ISSN: | 2162-237X 2162-2388 |
| Sprache: | Englisch |
| Schlagwörter: | Statistics; Machine Learning |
| Fachgebiet (DDC): | 006: Spezielle Computerverfahren |
| Zusammenfassung: | This work studies the class of algorithms for learning with side-information that emerge by extending generative models with embedded context-related variables. Using finite mixture models (FMM) as the prototypical Bayesian network, we show that maximum-likelihood estimation (MLE) of parameters through expectation-maximization (EM) improves over the regular unsupervised case and can approach the performances of supervised learning, despite the absence of any explicit ground truth data labeling. By direct application of the missing information principle (MIP), the algorithms' performances are proven to range between the conventional supervised and unsupervised MLE extremities proportionally to the information content of the contextual assistance provided. The acquired benefits regard higher estimation precision, smaller standard errors, faster convergence rates and improved classification accuracy or regression fitness shown in various scenarios, while also highlighting important properties and differences among the outlined situations. Applicability is showcased with three real-world unsupervised classification scenarios employing Gaussian Mixture Models. Importantly, we exemplify the natural extension of this methodology to any type of generative model by deriving an equivalent context-aware algorithm for variational autoencoders (VAs), thus broadening the spectrum of applicability to unsupervised deep learning with artificial neural networks. The latter is contrasted with a neural-symbolic algorithm exploiting side-information. |
| URI: | https://repository.essex.ac.uk/28199/ https://digitalcollection.zhaw.ch/handle/11475/20503 |
| Volltext Version: | Publizierte Version |
| Lizenz (gemäss Verlagsvertrag): | Lizenz gemäss Verlagsvertrag |
| Departement: | School of Engineering |
| Organisationseinheit: | Institut für Informatik (InIT) |
| Enthalten in den Sammlungen: | Publikationen School of Engineering |
Dateien zu dieser Ressource:
Es gibt keine Dateien zu dieser Ressource.
Zur Langanzeige
Perdikis, S., Leeb, R., Chavarriaga, R., & Millán, J. d. R. (2020). Context-aware learning for generative models. IEEE Transactions on Neural Networks and Learning Systems. https://doi.org/10.1109/TNNLS.2020.3011671
Perdikis, S. et al. (2020) ‘Context-aware learning for generative models’, IEEE Transactions on Neural Networks and Learning Systems [Preprint]. Available at: https://doi.org/10.1109/TNNLS.2020.3011671.
S. Perdikis, R. Leeb, R. Chavarriaga, and J. d. R. Millán, “Context-aware learning for generative models,” IEEE Transactions on Neural Networks and Learning Systems, Aug. 2020, doi: 10.1109/TNNLS.2020.3011671.
PERDIKIS, Serafeim, Robert LEEB, Ricardo CHAVARRIAGA und José del R. MILLÁN, 2020. Context-aware learning for generative models. IEEE Transactions on Neural Networks and Learning Systems [online]. 10 August 2020. DOI 10.1109/TNNLS.2020.3011671. Verfügbar unter: https://repository.essex.ac.uk/28199/
Perdikis, Serafeim, Robert Leeb, Ricardo Chavarriaga, and José del R. Millán. 2020. “Context-Aware Learning for Generative Models.” IEEE Transactions on Neural Networks and Learning Systems, August. https://doi.org/10.1109/TNNLS.2020.3011671.
Perdikis, Serafeim, et al. “Context-Aware Learning for Generative Models.” IEEE Transactions on Neural Networks and Learning Systems, Aug. 2020, https://doi.org/10.1109/TNNLS.2020.3011671.
Alle Ressourcen in diesem Repository sind urheberrechtlich geschützt, soweit nicht anderweitig angezeigt.