EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Combining Model-Agnostic Meta-Learning and Transfer Learning for Regression

Wahyu Fadli Satrya, Ji-Hoon Yun iD

Sensors · 04.01.2023 · 23 (2) · 583

DOI: 10.3390/s23020583 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 04.01.2023. Verfasst von Wahyu Fadli Satrya und 1 weiteren Autor:innen. Beteiligte Einrichtung: Computer Science Department, BINUS Online Learning, Bina Nusantara University, West Jakarta, Jakarta 11480, Indonesia. Hauptthemen laut MEDLINE: Acclimatization, Virtual Reality. Die Arbeit wurde bisher 26-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Institute of Information Communications Technology Planning & Evaluation, Institute of Information Communications Technology Planning & Evaluation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

For cases in which a machine learning model needs to be adapted to a new task, various approaches have been developed, including model-agnostic meta-learning (MAML) and transfer learning. In this paper, we investigate how the differences in the data distributions between the old tasks and the new target task impact performance in regression problems. By performing experiments, we discover that these differences greatly affect the relative performance of different adaptation methods. Based on this observation, we develop ensemble schemes combining multiple adaptation methods that can handle a wide range of data distribution differences between the old and new tasks, thus offering more stable performance for a wide range of tasks. For evaluation, we consider three regression problems of sinusoidal fitting, virtual reality motion prediction, and temperature forecasting. The evaluation results demonstrate that the proposed ensemble schemes achieve the best performance among the considered methods in most cases.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AcclimatizationVirtual RealityMachine LearningMotionTemperature

Stichwörter der Autor:innen

MAMLensemblefew-shot learningmeta-learningmodel adaptationmodel-agnostic meta-learningregressiontransfer learning

Autor:innen und Institutionen

  • Computer Science Department, BINUS Online Learning, Bina Nusantara University, West Jakarta, Jakarta 11480, Indonesia.
  • Department of Electrical and Information Engineering, Seoul National University of Science and Technology, Seoul 01811, Republic of Korea.

ORCID-Profile: Ji-Hoon Yun

Förderung

  • Institute of Information Communications Technology Planning & Evaluation
  • Institute of Information Communications Technology Planning & Evaluation

Zitieren

APA

Satrya, W. F., & Yun, J. H. (2023). Combining Model-Agnostic Meta-Learning and Transfer Learning for Regression. Sensors, 23(2), 583. https://doi.org/10.3390/s23020583

Vancouver

Satrya WF, Yun JH. Combining Model-Agnostic Meta-Learning and Transfer Learning for Regression. Sensors. 2023;23(2):583. doi:10.3390/s23020583

BibTeX
@article{Satrya2023,
  author = {Satrya, Wahyu Fadli and Yun, Ji-Hoon},
  title = {Combining Model-Agnostic Meta-Learning and Transfer Learning for Regression},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {2},
  pages = {583},
  doi = {10.3390/s23020583}
}
Kostenlos starten →